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 .
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 (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1, 10, 11 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Menard; Johnathan P. et al. (US 20230214455 A1), hereinafter MENARD, in view of Burgess; Harlow (US 20200243174 A1) , hereinafter BURGESS.
Examiner note: The US Patent Application MENARD was selected as the main reference because of the similarities regarding the record management system that utilize an Artificial Intelligence or Machine Learning model to execute various task and generate workflows for record processing. MENARD discloses features as generating recommended actions for the records, in some embodiments generate decisions for appeal of denied claims and automate the submission depending on a confidence score. The reference BURGESS teaches the use of a virtual agent (or chat bot) in order to conduct a conversation where the user can obtain information related to their records.
Regarding claim 1, MENARD teaches:
A method for managing and processing database records, the method comprising: maintaining, by a records management and processing system, a set of records in a database, each record of the set of records comprising a record of a service provided to a consumer by a service provider of a plurality of service providers and identifying at least one required action by at least one responsible entity of a plurality of responsible entities;
“FIG. 4 is a diagram illustrating the use of an AI/ML proactive model 407 as part of a claim submission system 400 according to an embodiment. In some embodiments, the claim submission system 400 may comprise an electronic medical record (EMR) platform 401, a claim cycle platform 402, and an artificial intelligence/machine learning platform 403 (for example, a proactive claims denial system). ...” (MENARD [0049])
“… For example, in some embodiments, claims data may be stored in a relational database, provided in text-based files such as CSV or TSV files, or provided in a structured format such as JavaScript Object Notation (JSON) or XML. …” (MENARD [0042])
“ In another embodiment, a system for tuning a claims resubmission predictive model is provided. The system comprises: one or more processors; a network communications interface; a memory; and computer code stored in the memory, wherein the computer code, when retrieved from the memory and executed by the one or more processors causes the one or more processors to: access a first set of electronic payer remit data associated with a first set of healthcare claims, a first plurality of patients, a second plurality of provider identifiers associated with providers of healthcare services, and a first payer entity associated with an entity that provide reimbursement or payment for healthcare services; ... ” (MENARD [0007])
maintaining, by the records management and processing system, a plurality of models and wherein the plurality of models are trained on historical processing of the plurality of records by the records management and processing system;
“ ... In other embodiments, the AI/ML proactive model can be generated and tuned using only the historical claims data of a specific provider. In such an embodiment, the AI/ML proactive claim processing system 400 may apply the AI/ML proactive model to claim submission data from a provider so that the provider receives predictions of the likelihood that the claims will be denied and the corresponding CARC based on the provider's own historical denials by the same payer. ... ” (MENARD [0046])
“ This disclosure describes embodiments of systems and methods that may be used to apply artificial intelligence and/or machine learning to identify and correct problems with claims and to help providers conduct automated decisioning and submit claims appeals for denied claims. In some embodiments, claims and remittance data may be collected from a plurality of providers including hospitals, medical groups, doctors, and/or other clinicians. This data may, in some embodiments, be used to train one or more artificial intelligence or machine learning models to recognize claims that are likely to be denied as to a specific set of payer systems and to generate one or more reason codes or decisioning tools to reduce denials. ... ” (MENARD [0032])
“ ... At block 1204, the AI/ML claims processing system 104 may apply one or more of the AI/ML proactive models to the claims submission data to generate corresponding probability data that indicate the likelihood of the claim being denied by the payer.... ” (MENARD [0079])
And processing, by the records management and processing system, the one or more records of the set of records according to one or more workflows executed by the records management and processing system,
“ The AI/ML reactive claim processing system 800 may cluster the denied claims based at least in part on the predicted approval probability indicator and the other requested parameters to generate one or more clusters, such as, for example, clusters for write-offs, clusters for immediate processing and resubmission, and/or clusters for potential processing and resubmission. The AI/ML reactive claim processing system 800 may generate workflow requests and populate workflow queues based on the one or more clusters. ” (MENARD [0068])
wherein the one or more workflows process the one or more records utilizing one or more Artificial Intelligence (Al) engines,
“ Embodiments of various systems, methods, and devices are disclosed for generating artificial intelligence or machine learning models for predicting denials of medical claims, predicting approvals of resubmitted medical claims, as well as automatic workflow clustering processes for automatically assigning medical claims to workflow queues using predictive segmentation and smart resource allocation. ” (MENARD [ABSTRACT])
and wherein at least one of the Al engines utilizes the plurality of models to perform at least one of generating a summary related to a record of the plurality of records,
Examiner note: This limitation is not being mapped to any of the previously mentioned references, since the claim is formulated with an OR operator, only one of the portions in the statement need to be satisfied in order for the limitation to be taught by the reference cited.
creating one or more automated or recommended next best actions for processing a record of the plurality of records,
“ … electronically identify a third set of claims of the first plurality of healthcare claims associated with the first payer entity where each claim in the third set of claims is associated with a prediction indicator of the set of claims denial production data that meet a second threshold indicating a high likelihood of being denied and associated with at least one denial reason indicating potential reasons for denial for the respective claim; generate at least one recommended corrected action for each of the claims in the third set of claims based on at least the at least one denial reason; generate instructions to present the at least one recommended corrected action for each of the claims in the third set of claims in a user interface for electronic approval by a first agent system; in response to receiving an electronic indication of the electronic approval by the first agent system, automatically implement the at least one recommended corrected action for each of the claims in the third set of claims; ... ” (MENARD [0005])
performing an automated appeals process for a record of the plurality of records,
“ This disclosure describes embodiments of systems and methods that may be used to apply artificial intelligence and/or machine learning to identify and correct problems with claims and to help providers conduct automated decisioning and submit claims appeals for denied claims. ... ” (MENARD [0032])
performing automated coding on a record of the plurality of records,
“ This disclosure describes embodiments of systems and methods that may be used to apply artificial intelligence and/or machine learning to identify and correct problems with claims and to help providers conduct automated decisioning and submit claims appeals for denied claims. In some embodiments, claims and remittance data may be collected from a plurality of providers including hospitals, medical groups, doctors, and/or other clinicians. This data may, in some embodiments, be used to train one or more artificial intelligence or machine learning models to recognize claims that are likely to be denied as to a specific set of payer systems and to generate one or more reason codes or decisioning tools to reduce denials. In some embodiments, aggregating claims and remittance data across a plurality of providers may allow for more accurate and fine-grained predictions (for example, aggregating data means that more combinations of procedures, policies, and so forth., are included in the data). In some embodiments, one or more systems may provide a denial probability and/or one or more predicted Claim Adjustment Reason Codes (CARCs) and/or Remittance Advice Remark Codes (RARCs). One or more of the systems may generate electronic flags or notifications of claims with a high probability of denial prior to submission. Provider systems may use said codes to generate instructions for intervening or modifying the claim prior to electronically submitting claims to the payer systems, thereby reducing the likelihood that the claims are denied. ” (MENARD [0032])
MENARD does not teach, but BURGESS teaches:
or conducting a communication session using a virtual agent.
“ … For example, in one embodiment, a user 110 may interact with the server 102 through a chat bot operating within a social network or through text messaging on a cellular network. In some embodiments, interactions through secondary networks may be limited in nature due to security and privacy regulations surrounding health records. As a specific example, in some embodiments, the system 100 is configured to be HIPAA compliant. ” (BURGESS [0040])
” According to various embodiments, the database 104 may also comprise reference data 210. As will be discussed in greater detail below with respect to FIG. 4, some embodiments of the system 100 may comprise an integrated help system. In some embodiments, it may take the form of a conversational “chat bot”, or virtual agent, with which users can converse and ask questions. In some embodiments, the healthcare document management system 100 contemplated herein not only helps users 110 manage their medical documents, but also provide greater clarity with respect to the healthcare system as a whole, put into the context of that particular user 110 or patient. The reference data 210 may take the form of any expert systems or reference systems known in the art. ” (BURGESS [0046])
It would have been obvious to someone of ordinary skill in the art before the effective filling date of the claimed invention to include in the teachings of MENARD the capability to include a virtual agent interface to interact with the records using natural language. The benefit and motivation of such modification is discussed by BURGESS in the following portion: “ In some embodiments, users 110 may be provided support through an automated chat bot. Using natural language processing, the automated chat bot allows users to ask questions and receive relevant answers in a manner that is not intimidating or rigid like conventional automated support systems. The server 102 receives, from the client device 106, a query 412 made by the user using natural language. In some embodiments, the interface may resemble a text messaging conversation, while in other embodiments the user 110 may interact with the bot using voice recognition and text-to-speech technologies. In one embodiment, the user 110 may interact with the chat bot through a voice phone call. ” (BURGESS [0108])
Regarding claim 10, the rejection of claim 1 is incorporated, furthermore MENARD does not teach, but BURGESS teaches:
The method of claim 1, wherein conducting a communication session using a virtual agent comprises: initiating a natural language communication session;
“ ...The document management server may be further configured to receive, from the user client device, a query made by the user in natural language, parse the query, search the database for data associated to the parsed query, and/or send data associated to the parsed query to the user client device. ... ” (BURGESS [0006])
identifying, using Natural Language Processing (NLP), an intent for the natural language communication session;
“ In some embodiments, users 110 may be provided support through an automated chat bot. Using natural language processing, the automated chat bot allows users to ask questions and receive relevant answers in a manner that is not intimidating or rigid like conventional automated support systems. The server 102 receives, from the client device 106, a query 412 made by the user using natural language. In some embodiments, the interface may resemble a text messaging conversation, while in other embodiments the user 110 may interact with the bot using voice recognition and text-to-speech technologies. In one embodiment, the user 110 may interact with the chat bot through a voice phone call. ” (BURGESS [0108])
identifying one or more parties that are subjects of the natural language communication session;
“ Going forward, reference is made to a user 110 of the system 100. In the context of the present description and the claims that follow, a user 110 is an individual interfacing or interacting with the system 100 on behalf of a recipient of medical services. A user 110 may or may not also be a patient. For example, in some embodiments, the system 100 may be used to manage the documents and benefits for a family, meaning the user 110 may be a parent organizing the bills associated with the treatment of their child, the patient. ” (BURGESS [0033])
“ As a specific example, in some embodiments, the server 102 may be configured to quickly integrate with other parties, such as providers 116 and insurance companies 118, in multiple ways, to facilitate their interaction with the system 100 and provide quick benefit to the users 110. For example, the server 102 may be able to interact with these parties without any disruption to their existing systems and business practices. ” (BURGESS [0042])
collecting, from a plurality of information sources, supporting information related to the natural language communication session and based on the identified intent for the natural language communication session and the identified one or more parties that are subjects of the natural language communication session;
“ Upon receiving the query 412, the server 102 parses it using natural language processing, identifying the desired data. The reference data 210 in the database 104 is searched for data 414 associated with the parsed query. See circle ‘11’. The server 102 renders a natural language answer 416 to the query using the data 414 associated with the parsed query. The answer 416 is sent back to the user client device 106. ” (BURGESS [0109])
generating, using a Large Language Model (LLM), a natural language summary of the natural language communication session and the collected supporting information;
“ In some embodiments, users 110 may be provided support through an automated chat bot. Using natural language processing, the automated chat bot allows users to ask questions and receive relevant answers in a manner that is not intimidating or rigid like conventional automated support systems. The server 102 receives, from the client device 106, a query 412 made by the user using natural language. In some embodiments, the interface may resemble a text messaging conversation, while in other embodiments the user 110 may interact with the bot using voice recognition and text-to-speech technologies. In one embodiment, the user 110 may interact with the chat bot through a voice phone call. ” (BURGESS [0108])
“ In some embodiments, the server 102 may look to other sources of data when forming the answer 416 to the query 412. For example, in some embodiments, the server 102 may contact a third party server 115 to obtain general information (e.g. information regarding a procedure code, information regarding the coverage of a particular insurance plan, etc.). In some embodiments, the server 102 may draw information from the user record 200 when formulating the answer 416, allowing the system 100 to provide an answer to a user's question that is specific to them and their situation, without requiring them to take a general answer and figure out how to apply it to their particular situation, as done in conventional automated support systems” (BURGESS [0111])
Wherein the summary disclosed is represented by the NLP answer that the chat bot disclosed in BURGESS provide to the user, wherein the answer is a short version of all the information analyzed to generate it (for example the user record, the medical procedure and the information regarding the coverage of a particular insurance plan.
and providing the natural language summary to the one or more workflows for processing of the record.
“ Upon receiving the query 412, the server 102 parses it using natural language processing, identifying the desired data. The reference data 210 in the database 104 is searched for data 414 associated with the parsed query. See circle ‘11’. The server 102 renders a natural language answer 416 to the query using the data 414 associated with the parsed query. The answer 416 is sent back to the user client device 106. ” (BURGESS [0109])
It would have been obvious to someone of ordinary skill in the art before the effective filling date of the claimed invention to include in the teachings of MENARD the capability to include a virtual agent interface to interact with the records using natural language. The benefit and motivation of such modification is discussed by BURGESS in the following portion: “ In some embodiments, users 110 may be provided support through an automated chat bot. Using natural language processing, the automated chat bot allows users to ask questions and receive relevant answers in a manner that is not intimidating or rigid like conventional automated support systems. The server 102 receives, from the client device 106, a query 412 made by the user using natural language. In some embodiments, the interface may resemble a text messaging conversation, while in other embodiments the user 110 may interact with the bot using voice recognition and text-to-speech technologies. In one embodiment, the user 110 may interact with the chat bot through a voice phone call. ” (BURGESS [0108])
Regarding claim 11, arguments analogous to claim 1 are applicable (see rejection of claim 1 above), furthermore MENARD teaches:
A system comprising: a processor; and a memory coupled with and readable by the processor and storing therein a set of instructions which, when executed by the processor, causes the processor to:
“ In one embodiment, a system for tuning a claims remittance prediction model is provided. The system comprises: one or more processors; a network communications interface; a memory; and computer code stored in the memory, wherein the computer code, when retrieved from the memory and executed by the one or more processors causes the one or more processors to: ... ” (MENARD [0004])
Regarding claim 20, the rejection of claim 10 is incorporated, furthermore arguments analogous to claim 10 are applicable.
Claims 2 to 6 and 12 to 16 are rejected under 35 U.S.C. 103 as being unpatentable over MENARD in view of BURGESS in further view of Hasan; Sheikh Sadid Al et al. (US 20230352134 A1) hereinafter HASAN.
Examiner note: The reference HASAN is included in this rejection because of the teachings related to record summaries using natural language, a deeper next-best action analysis and the incorporation of clinical feedback in order to train a model.
Regarding claim 2, the rejection of claim 1 is incorporated, furthermore MENARD in view of BURGESS does not explicitly disclose, but HASAN teaches:
The method of claim 1, wherein generating a summary related to a record of the plurality of records comprises: reading the record of the plurality of records;
“ A method of automatically generating a patient care plan includes: providing data inputs to a machine learning model, where the data inputs include electronic patient data obtained from a plurality of electronic records describing a health history of the patient; …” (HASAN [0004])
providing the record of the plurality of records to a generative Al engine of the one or more Al engines, wherein the generative Al produces one or more natural language summaries of previous actions taken in the processing of the record and notes associated with the record;
“ Accordingly, for example, the system 100 supports leveraging holistic member information to recommend personalized and prioritized recommendations 314 (e.g., personalized and prioritized opportunities). For example, the care recommendation engine 183 may gain an understanding of the member (e.g., regarding risk triggers, clinical impact factors, previous healthcare utilization, etc.) based on the profile summary 310. Additionally, or alternatively, the system 100 may support providing the profile summary 310 to the care manager for review. In another example, the system 100 may provide the set of top recommendations 320 (e.g., in a report, for example, in an electronic communication 155 of FIG. 1) to the care manager, based on which the care manager may identify areas of concern for the member and highly impactable (e.g., valuable) opportunities for the member. Additionally or alternatively, the system 100 may support providing top recommendations and context for the top recommendations such that the care manager does not need to analyze why a recommendation was provided. ” (HASAN [0148])
receiving the one or more natural language summaries from the generative Al engine;
“ The healthcare system includes example implementations of an AI-based clinical decision support solution that integrates care opportunities from the various sources (e.g., care considerations, next best actions, etc.) to generate personalized and prioritized recommendations along with member health summaries to support care manager case preparation and care planning. In some examples, the AI-based clinical decision support solution may support advanced machine learning algorithms to generate holistic member health summaries from various data sources (e. g. tele-home assessments, in-home assessments, claims, assessments, labs, SDoH, etc.). AI-based clinical decision support solutions described herein may include causal inference modeling to generate personalized and prioritized recommendations. Examples of providing a care plan for a member according to the present disclosure are later described herein with respect to the following figures. ” (HASAN [0050])
and providing the one or more natural language summaries to the one or more workflows for processing of the record.
“ In some aspects, the recommendation summary is generated, at least in part, with a natural language generation (NLG) model. ” (HASAN [0024])
“ At 545, the process flow 500 may include automatically generating a recommendation summary (e.g., recommendation summary 158 of FIG. 1) that includes a summarized description of the one or more recommended patient actions for the patient. In some aspects, the recommendation summary includes an additional summarized description of the at least one additional recommended patient action. ” (HASAN [0187])
“ At 510, the process flow 500 may include receiving an output from the machine learning model. In some aspects, the output received from the machine learning model is generated based on the machine learning model processing the data inputs and includes a plurality of identified care gaps for the patient. ” (HASAN [0177])
It would have been obvious to someone of ordinary skill in the art before the effective filling date of the claimed invention to include in the teachings of MENARD in view of BURGESS the capability to generate record summaries using natural language. The benefit and motivation of such modification is discussed by HASAN in the following portion: “ Accordingly, for example, the system 100 supports leveraging holistic member information to recommend personalized and prioritized recommendations 314 (e.g., personalized and prioritized opportunities). For example, the care recommendation engine 183 may gain an understanding of the member (e.g., regarding risk triggers, clinical impact factors, previous healthcare utilization, etc.) based on the profile summary 310. Additionally, or alternatively, the system 100 may support providing the profile summary 310 to the care manager for review. In another example, the system 100 may provide the set of top recommendations 320 (e.g., in a report, for example, in an electronic communication 155 of FIG. 1) to the care manager, based on which the care manager may identify areas of concern for the member and highly impactable (e.g., valuable) opportunities for the member. Additionally or alternatively, the system 100 may support providing top recommendations and context for the top recommendations such that the care manager does not need to analyze why a recommendation was provided. ” (HASAN [0148])
Regarding claim 3, the rejection of claim 2 is incorporated, furthermore MENARD in view of BURGESS does not explicitly disclose, but HASAN teaches:
The method of claim 2, further comprising: receiving, by the records management and processing system, feedback related to the one or more natural language summaries;
“ At 565, the process flow 500 may include providing the clinician feedback as training data to the machine learning model. ” (HASAN [0198])
“ The system 100 may provide model improvement 215 based on feedback (e.g., feedback 159 described with reference to FIG. 1) provided by a care manager in association with the care recommendations 210. For example, model improvement 215 may include testing and learning, implemented by the system 100, that supports iterative improvement of subsequent recommendation results (e.g., subsequent care recommendations 210) generated by the care recommendation engine 183 based on the feedback. ” (HASAN [0129])
And training, by the records management and processing system, the generative Al with the feedback related to the one or more natural language summaries.
“ Some examples include: receiving clinician feedback for the one or more recommended patient actions; providing the clinician feedback as training data to the machine learning model; and updating at least one coefficient of the machine learning model based on providing the training data to the machine learning model. ” (HASAN [0016])
It would have been obvious to someone of ordinary skill in the art before the effective filling date of the claimed invention to include in the teachings of MENARD in view of BURGESS the capability to collect feedback from the generated record summaries train a natural language model. The benefit and motivation of such modification is discussed by HASAN in the following portion: “ Various example aspects described herein may be applied to various types of healthcare organizations. Aspects of the present disclosure may be applied to supporting providers with member health summaries towards obtaining better health outcomes for the members through enabling access to healthcare via provider partners, examples of which are described in Exhibit A. ” (HASAN [0259])
Regarding claim 4, the rejection of claim 2 is incorporated, furthermore MENARD in view of BURGESS does not explicitly disclose, but HASAN teaches:
The method of claim 2, wherein creating one or more automated or recommended next best actions for processing a record of the plurality of records comprises: generating a plurality of suggested next actions for processing of the record based on the one or more natural language summaries and one or more of the plurality of models;
“ In some aspects, the one or more recommended patient actions may include a next best action for the patient to take in connection with closing a care gap from the plurality of identified care gaps. In some aspects, the next best action is associated with closing more than one care gap from the plurality of identified care gaps. In some aspects, the next best action corresponds to an action that is predicted most likely to be taken by the patient. In some aspects, the next best action corresponds to at least one of the following: a visit to a healthcare provider, a change in a medical treatment, a change in a prescription, a change in diet, a change in activity, a blood test, and a medical examination. ” (HASAN [0193])
“At 575, the process flow 500 may include replacing the machine learning model with an updated version of the machine learning model. In some aspects, the updated version of the machine learning model may include the updated at least one coefficient. ” (HASAN [0200])
determining, by one or more Al engines of the plurality of Al engines, a probability of completing processing of the record for each of the plurality of suggested next actions based on execution of the suggested next action;
“In another example, at 590, the process flow 500 may include, if the patient took the next best action within the predetermined amount of time, determining whether the next best action resulted in a partial or complete closing of the care gap. ” (HASAN [0203])
“ At 595, the process flow 500 may include updating a recommendation library based on whether the next best action results in a partial or complete closing of the care gap. ” (HASAN [0204])
“ In some aspects, the selected communication channel is selected based on a probability of closing a care gap having the highest treatment effect score and in some aspects, the selected communication channel may include at least one of email, direct mail, SMS, and an automated outbound calling campaign. ” (HASAN [0196])
scoring each of the plurality of suggested next actions based on the determined probability of completing processing of the record for the suggested next action;
“ In some aspects, the server 135 may receive the guideline behavior for the member supported by a professional clinical recommendation. For example, the server 135 may receive and/or access the guideline behavior from a communication device 105, the provider database 145, the member database 150, and/or another server 135. In some examples, the guideline behavior for the member supported by the professional clinical recommendation may include guidance based on at least one of medical history, demographics, social indices, biomarkers, behavior data, engagement data, historical gap-in-care data, and a machine learning model-derived output (e.g., a risk-based model probability derived by a machine learning model(s) 184 described herein). In some aspects, the guidance may be based on medical history, demographics, social indices, biomarkers, behavior data, engagement data, historical gap-in-care data, and/or machine learning model-derived output(s) that correspond to the member and/or other members. ” (HASAN [0081])
“ At 520, the process flow 500 may include, based on the treatment effect determined for each of the plurality of identified care gaps, assigning a treatment effect score to each of the plurality of identified care gaps. ” (HASAN [0179])
selecting one or more next actions from the plurality of suggested next actions based on the scoring of each of the plurality of suggested next actions;
“ A method of automatically generating a patient care plan includes: providing data inputs to a machine learning model, where the data inputs include electronic patient data obtained from a plurality of electronic records describing a health history of the patient; receiving an output from the machine learning model, where the output received from the machine learning model is generated based on the machine learning model processing the data inputs and includes a plurality of identified care gaps for the patient; determining a treatment effect for each of the plurality of identified care gaps; based on the treatment effect determined for each of the plurality of identified care gaps, assigning a treatment effect score to each of the plurality of identified care gaps; prioritizing the plurality of identified care gaps based on the treatment effect score assigned thereto; based on the prioritization of the plurality of identified care gaps, determining one or more recommended patient actions for the patient; generating an electronic communication that describes the one or more recommended patient actions for the patient; and transmitting the electronic communication via a communication network to a communication device. ” (HASAN [0004])
And providing the selected one or more actions to the one or more workflows for processing of the record.
“ At 595, the process flow 500 may include updating a recommendation library based on whether the next best action results in a partial or complete closing of the care gap. ” (HASAN [0204])
It would have been obvious to someone of ordinary skill in the art before the effective filling date of the claimed invention to include in the teachings of MENARD in view of BURGESS the capability to use the generated record summaries to generate next-best actions suggestions for the records using natural language. The benefit and motivation of such modification is discussed by HASAN in the following portion: “ In some aspects, the one or more recommended patient actions may include a next best action for the patient to take in connection with closing a care gap from the plurality of identified care gaps. In some aspects, the next best action is associated with closing more than one care gap from the plurality of identified care gaps. In some aspects, the next best action corresponds to an action that is predicted most likely to be taken by the patient. In some aspects, the next best action corresponds to at least one of the following: a visit to a healthcare provider, a change in a medical treatment, a change in a prescription, a change in diet, a change in activity, a blood test, and a medical examination. ” (HASAN [0193])
Regarding claim 5, the rejection of claim 4 is incorporated, furthermore MENARD in view of BURGESS does not explicitly disclose, but HASAN teaches:
The method of claim 4, further comprising: receiving feedback related to the selected one or more actions;
“ The system 100 may provide model improvement 215 based on feedback (e.g., feedback 159 described with reference to FIG. 1) provided by a care manager in association with the care recommendations 210. For example, model improvement 215 may include testing and learning, implemented by the system 100, that supports iterative improvement of subsequent recommendation results (e.g., subsequent care recommendations 210) generated by the care recommendation engine 183 based on the feedback. ” (HASAN [0129])
And training the one or more Al engines based on the feedback.
“ In some aspects, the one or more recommended patient actions for the patient are generated, at least in part, using a heterogeneous treatment effect (HTE) model. In some aspects, the HTE model is updated using a reinforcement learning-based formulation that dynamically updates the HTE model based on clinician feedback while the HTE model is being used to generate the one or more recommended patient actions. ” (HASAN [0191])
It would have been obvious to someone of ordinary skill in the art before the effective filling date of the claimed invention to include in the teachings of MENARD in view of BURGESS the capability to train a natural language model using the feedback collected from the next-best action recommendation. The benefit and motivation of such modification is discussed by HASAN in the following portion: “ In some aspects, the processors (e.g., processor 110, processor 160) may support machine learning model(s) 184 which may be trained and/or updated based on data (e.g., training data 186) provided or accessed by any of the communication device 105, the server 135, the provider database 145, and the member database. The machine learning model(s) 184 may be built and updated by any of the engines (e.g., member profile engine 181, care gap management engine 182, care recommendation engine 183, SDoH recommendation engine 191, etc.) described herein based on the training data 186 (also referred to herein as training data and feedback). For example, the machine learning model(s) 184 may be trained with feature vectors of members (e.g., accessed from provider database 145 or member database 150) for which adherence to one or more recommended actions 157 (e.g., care recommendations) reduced a corresponding gap-in-care and/or achieved one or more impacts (e.g., cost impact, clinical impact, reduction in inpatient visits, etc.). In some examples, the machine learning model(s) 184 may be trained with additional feature vectors of members (e.g., accessed from provider database 145 or member database 150) for which adherence to one or more SDoH recommendations 156 reduced a corresponding gap-in-care and/or achieved one or more impacts. ” (HASAN [0088])
Regarding claim 6, the rejection of claim 4 is incorporated, furthermore MENARD teaches:
The method of claim 4, wherein the one or more workflows automatically execute the selected one or more actions.
“ Embodiments of various systems, methods, and devices are disclosed for generating artificial intelligence or machine learning models for predicting denials of medical claims, predicting approvals of resubmitted medical claims, as well as automatic workflow clustering processes for automatically assigning medical claims to workflow queues using predictive segmentation and smart resource allocation. ” (MENARD [ABSTRACT])
“ ... generate at least one recommended corrected action for each of the claims in the third set of claims based on at least the at least one denial reason; generate instructions to present the at least one recommended corrected action for each of the claims in the third set of claims in a user interface for electronic approval by a first agent system; in response to receiving an electronic indication of the electronic approval by the first agent system, automatically implement the at least one recommended corrected action for each of the claims in the third set of claims; ... ” (MENARD [0010])
Regarding claim 12, the rejection of claim 11 is incorporated, furthermore arguments analogous to claim 2 are applicable.
Regarding claim 13, the rejection of claim 12 is incorporated, furthermore arguments analogous to claim 3 are applicable.
Regarding claim 14, the rejection of claim 12 is incorporated, furthermore arguments analogous to claim 4 are applicable.
Regarding claim 15, the rejection of claim 14 is incorporated, furthermore arguments analogous to claim 5 are applicable.
Regarding claim 16, the rejection of claim 14 is incorporated, furthermore arguments analogous to claim 6 are applicable.
Claims 7, 9, 17 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over MENARD in view of BURGESS in further view of PRIESTAS; James Robert et al. (US 20200364404 A1) hereinafter PRIESTAS.
Examiner note: The reference PRIESTAS is included in this rejection because of their disclosure of automatically generated natural language claim appeal letters that describe the claim.
Regarding claim 7, the rejection of claim 4 is incorporated, furthermore MENARD teaches:
The method of claim 1, wherein performing an automated appeals process for a record of the plurality of records comprises: generating a claim for the record, the claim defining a denial by a responsible entity in the processing of the record;
“ This disclosure describes embodiments of systems and methods that may be used to apply artificial intelligence and/or machine learning to identify and correct problems with claims and to help providers conduct automated decisioning and submit claims appeals for denied claims. ... ” (MENARD [0032])
classifying a denial type for the denial defined in the claim;
“ … electronically process the first set of electronic payer remit data to associate each remit data item with at least one of the first set of healthcare claims and an outcome status indicating either approval or denial for each respective healthcare claim to generate a set of denied claims whose outcome status indicates denial; ... ” (MENARD [0007])
determining, based on the generated claim and the denial type, whether the claim is valid;
“ FIG. 7 is an example user interface for displaying one or more potential denial reasons of a flagged claim to a user according to an embodiment. In the example interface depicted, users may be shown a claim submission view 700 which may include a data band 701 comprising information about the patient and/or information about the patient's insurance. The data band 701 may include an indicator that there may be one or more potential issues with the data in the data band 701 that could result in claim denial such as, for example, an incorrect name, an invalid address, an invalid insurance policy number, an expired insurance policy, or the like. The claim submission view 700 may further comprise a list of claim items 702 such as, for example, procedures, medical supplies, medications, hospital room charges, and the like. The list of claim items 702 may include one or more indicators for each of the one or more claim items indicating that there may be one or more issues with claim items that may result in claim denial. The claim submission view 700 may further comprise a denial view 703 which may comprise denial probability scores 704, denial reason descriptions 705, radio buttons 706, and severity indicators 707. In some embodiments, the severity indicators 707 may change based on the denial probability scores 704. ... ” (MENARD [0056])
And providing the generated submission packet to a responsible entity system for the responsible entity.
“ … send, via the network communication interface, the third encrypted data claim submission package to the first communications interface associated with the first payer entity; ...” (MENARD [0004])
MENARD in view of BURGESS does not teach, but PRIESTAS teaches:
in response to determining the claim is valid: generating, by the generative Al engine, a natural language letter describing the claim;
“ Various components of the data processing system 100 can access or generate one or more graphical user interfaces (GUIs) 160 which can be used for various user interactions. For example, one of the GUIs 160 can be used to transmit the request 102 while another one of the GUIs displays the data 108 extracted from the request 102. An output 114 that is generated may depend on the automated data processing task executed by the document processing system 100. If the automated document processing task 112 relates to an insurance claim, then the output 114 can include the recommendation 140. If the automated document processing task relates to a provider denial of a claim, the output 114 may additionally include an automatically generated letter 116 which appeals the denial to the provider along with the requisite documentation. In an example, the documentation accompanying the letter 116 may include documents extracted from the request 102 or documents obtained from the external data sources 150. Output 114 can include other types of data and/or information based on a given configuration of system 100. ” (PRIESTAS [0023])
“ ... For example, if the request 102 pertains to a worker's compensation claim, the message 104 may include details regarding the party making the claim, claim identification details such as claim number, policy number, dates, etc. The documentation 106 associated with the claim can include the claimant's work identification, the claimant's medical records, letters from the medical providers such as the doctors, etc. Similarly, if the request 102 pertains to a casualty insurance claim associated with a theft for example, the message 104 may include text describing the claim including claim details such as the claim number, policy number, claimant name, place associated with the theft, the claimants address, etc. The documents 106 can include a police report, a formal valuation of the goods stolen, copies of the policy documents, etc. ” (PRIESTAS [0021])
generating a submission packet comprising the generated natural language letter and one or more pieces of content supporting the claim;
“ FIG. 10 shows an example provider denial appeals letter 1000 that is automatically generated in accordance with the examples disclosed herein. The appeals letter 1000 includes a patient details section 1002 that is automatically filled with the attributes 942 gathered from the patient's file or documents. In addition to general attributes such as patient name, date of birth, member id, etc., specific details regarding a particular service pertaining to the denied matter such as the Hospital, dates of service, billed amount, etc., are also included in the patient details section 1002. In an example, a template of the letter may be stored in one of the data store 170, or the external data sources 150 can be retrieved. The template includes predetermined or standard language appealing the provider denial with place holders within the standard language for receiving at least a subset of the responsive data extracted from one or more of the request 102 and the external data sources 150. For example, the patient details section 1002 may include such place holders which are completed with the corresponding patient details retrieved from the request 102 and/or the external data sources 150. In an example, the tokens corresponding to the place holders can be identified using named entity recognition (NER), tokens from the responsive data 196, and the letter 1000 is generated with the tokens inserted or included in the corresponding place holders. ” (PRIESTAS [0046])
It would have been obvious to someone of ordinary skill in the art before the effective filling date of the claimed invention to include in the teachings of MENARD in view of BURGESS the capability to generate letters based on the record to describe the claim using natural language. The benefit and motivation of such modification is discussed by PRIESTAS in the following portion: “ Embodiments of the invention can be configured to address health payer use cases, such as provider claims and disputes. For example, document processing system 100 can be configured to review provider disputes and claims. For example, provider responses from claim denials can be reviewed for adjudication. Appeal letters for provider denials or other letters can be automatically generated as described above. Another health payer application of the document processing system 100 can include provider data management. ” (PRIESTAS [0050])
Regarding claim 9, the rejection of claim 1 is incorporated, furthermore MENARD teaches:
providing the one or more codes and the record to the one or more workflows for processing of the record;
“ In some embodiments, the artificial intelligence/machine learning platform 403 may then apply an ensemble of AI/ML proactive models to the set of claims based on a provider associated with each of the claims to generate predictions for the likelihood of the claims being denied by the respective payer(s) and the corresponding CARC(s). The artificial intelligence/machine learning platform 403 may then, through the API 406, provide an electronic set of results data back to the claim cycle platform 402. The electronic set of results data may include, for example, one or more predicted denial reason indicators, one or more predicted denial probability indicators, and/or one or more problems with the set of claims. In some embodiments, the artificial intelligence/machine learning platform 403 or the claim cycle platform 402 may perform automated updating to change or modify some of the claims and/or automated routing to send some of the claims to a workflow queue for additional review or processing. ... ” (MENARD [0050])
MENARD in view of BURGESS does not explicitly disclose, but PRIESTAS teaches:
The method of claim 1, wherein performing automated coding on a record of the plurality of records comprises: ingesting natural language data related to the record from a plurality of data sources;
“ In some examples, the document processing system 100 can be used to address health provider use cases such as Starts and Healthcare Effectiveness Data and Information Set (HEDIS) Chart Review. Employers and individuals use HEDIS to measure the quality of health plans. HEDIS measures how well health plans give service and care to their members. In addition to evaluating healthcare plans, the document processing system 100 can also be configured to review medical records and Health Level Seven (HL7) messages for quality measures. HL7 International specifies a number of flexible standards, guidelines, and methodologies by which various healthcare systems can communicate with each other. Such guidelines or data standards are a set of rules that allow information to be shared and processed in a uniform and consistent manner. These data standards are meant to allow healthcare organizations to easily share clinical information. Again, the request 102 can include medical records and/or HL7 messages while the quality measures (i.e., the guidelines 194) can be retrieved from the external data sources 150. The document processing system 100 can extract the responsive data 196 for the requirements specified in the quality measures and generate the recommendation 140 on whether the medical records or the HL7 messages meet the requirements of the quality measures. ” (PRIESTAS [0051])
analyzing the preprocessed natural language data related to the record using a Large Language Model (LLM) of the plurality of models;
“ Upon identifying the specific automatic document processing task to be executed, guidelines for the execution are retrieved from one or more external data sources. The guidelines can include requirements such as data requirements for the execution of the automatic document processing task. A plurality of machine learning (ML) models are used to extract data responsive to the requirements. Each of the ML models corresponds to a respective guideline and is trained to extract data that fulfill requirements the guideline. Different ML models based on different algorithms can be trained to extract the responsive data. The ML model that corresponds to a guideline will depend on the type of data that is responsive to that guideline. In an example, a plurality of ML models can be trained on labeled training data generated by subject matter experts for each of the plurality of ML models. In an example, the labeled training data from different documents in historical records includes data that is identified as responsive to each of the requirements of a given guideline. ” (PRIESTAS [0018])
identifying one more entities associated with the record based on results of analyzing the preprocessed natural language data related to the record;
“ The process analyzer 124 accesses the data 108 obtained by the request preprocessor 122 to identify an automatic document processing task to be executed. As mentioned above, the data 108 can include a process identifier 132 relating to the processes to be executed. Depending on the automatic document processing task to be executed one or more of the process identifier 132, e.g., certain keywords, member identifiers, etc. While the description herein generally refers to the process identifier 132 as enabling identification of the automatic document processing task, other process identifiers may also be used in accordance with some examples disclosed herein. In an example, a policy can pertain to an insurance policy associated with a workers' compensation claim. Upon the process identifier 132 identifying the policy pertaining to the request 102, the guidelines retriever 126 retrieves guidelines 194 associated with the policy. In an example, the guidelines 194 can be retrieved from one of the external data sources 150 that pertains to the policy. Therefore, different policies may necessitate retrieval of the guidelines 194 from different external data sources. In an example, the guidelines 194 retrieved from one of the external data sources 150 may be cached temporarily on the data store 170 during the execution of the automatic document processing task 112. The guidelines 194 can include certain data requirements that need to be met if the automatic document processing task is to be executed. Referring again to the worker's compensation request example, the corresponding guidelines can include data requirements for the claimant's information such as name, social security number, address, employer information, type of job, date of injury, nature of injury, etc. In addition, the guidelines 194 can also include requirements for clinical data and medical history of the claimant. The responsive data 196 per the requirements of the guidelines 194 is extracted from one or more of the data 108 and the external data sources 150 by the data extractor 128 using a plurality of ML models 138. In an example, each of the requirements and/or the guidelines 194 can be associated with a corresponding ML model that is trained to identify information responsive to the requirement. ” (PRIESTAS [0025])
validating the one or more codes based on a set of predefined standards;
“ The responsive data 196 obtained by the data extractor 136 along with the recommendation 140 can be presented for validation via a validation GUI 454 generated by the data validator 404. In an example, the validation GUI 454 can present one or more of the discrete data items from the responsive data 196 in an editable format so that a human reviewer who is validating can make any necessary changes to the data. In an example, the validation GUI 454 can include two portions where the extracted data is presented in a first portion and a corresponding view of the original data source, such as, a document, a database table or an image, etc., obtained from either the request 102 or the external data source from which the data piece was extracted can be displayed in a second portion. In an example, the validation GUI 454 can also include the recommendation 140 to approve or reject a claim associated with the request 102. A human validator may agree or disagree with the recommendation 140. The feedback from the human validator including any edits to the responsive data 196 can be provided to the document processing system 100 for further training. ” (PRIESTAS [0035])
“The document processing system 100 can be employed for Medical Record Processing at the Centers for Medicare and Medicaid Services, Military Health System, etc., and for Risk Adjustment Data Validation in a use case. The document processing system 100 can be configured to review medical records for processing for example, at Centers for Medicare and Medicaid Services (CMS), Military Health System, etc. Furthermore, the document processing system 100 can also be employed for Risk Adjustment Data Validation (RADV). …” (PRIESTAS [0072])
receiving feedback on the one or more codes;
“ The responsive data 196 obtained by the data extractor 136 along with the recommendation 140 can be presented for validation via a validation GUI 454 generated by the data validator 404. In an example, the validation GUI 454 can present one or more of the discrete data items from the responsive data 196 in an editable format so that a human reviewer who is validating can make any necessary changes to the data. In an example, the validation GUI 454 can include two portions where the extracted data is presented in a first portion and a corresponding view of the original data source, such as, a document, a database table or an image, etc., obtained from either the request 102 or the external data source from which the data piece was extracted can be displayed in a second portion. In an example, the validation GUI 454 can also include the recommendation 140 to approve or reject a claim associated with the request 102. A human validator may agree or disagree with the recommendation 140. The feedback from the human validator including any edits to the responsive data 196 can be provided to the document processing system 100 for further training. ” (PRIESTAS [0035])
And training at least one model of the plurality of models using the received feedback on the one or more codes.
“FIG. 7 shows a flowchart 700 that details a method of training the plurality of ML models 138 for extracting the data in accordance with the examples disclosed herein. At 702, one of the plurality of ML models 138 corresponding to one of the guidelines 194 is accessed. Each of the guidelines 194 can have corresponding one or more of the plurality of ML models 138 trained to provide data responsive to the guidelines based on a type of data that is expected. If the guideline expects text data in specific patterns such as social security numbers, dates, policy numbers, etc. then classification ML models suitable for prediction of textual data can be selected and trained to identify textual data in the specific pattern. If the guideline requires image data to be identified, then image classification ML models such as CNNs, deep learning networks (DLNs), etc. can be employed. In certain other examples, ensemble models based on two or more ML algorithms may also be employed. Accordingly, large volumes of training data for each of the plurality of ML models 138 that correspond to the type of data to be predicted by the ML model needs to be generated. At 704, data that was gathered and/or generated during prior document processing tasks which are similar to the document processing task 112 can be accessed. For example, documents pertaining to previously approved, settled, or rejected insurance claims can be digitized (i.e., scanned and text made machine-readable and machine searchable) and used to generate the training data 146. The training data 146 thus generated can be split into training data and test data. The collected data is used to train the plurality of ML models 138 and the test data can be used to test the trained ML model. Generally, the collected data is partitioned so that 80% of the data is training data while 20% of the data is used for testing the trained model. ” (PRIESTAS [0041])
It would have been obvious to someone of ordinary skill in the art before the effective filling date of the claimed invention to include in the teachings of MENARD in view of BURGESS the capability to perform the record coding evaluation and verification, receive feedback from the evaluation and train a model. The benefit and motivation of such modification is discussed by PRIESTAS in the following portion: “...Therefore, the document processing system 100 can analyze the codes and correlate the tests to diagnoses to ensure correct reimbursement. In case there are any discrepancies, the reimbursements may be denied and the provider denial process may be activated at that point. ” (PRIESTAS [0055])
Regarding claim 17, the rejection of claim 11 is incorporated, furthermore arguments analogous to claim 7 are applicable.
Regarding claim 19, the rejection of claim 11 is incorporated, furthermore arguments analogous to claim 9 are applicable.
Claims 8 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over MENARD in view of BURGESS in view of PRIESTAS in view of HASAN in further view of Schouten; Pieter et al. (US 20220292100 A1) hereinafter SCHOUTEN.
Examiner note: SCHOUTEN disclosure is utilized in this rejection because of the teachings of the prompt generation to acquire information related to the record.
The applied reference has a common assignee with the instant application. Based upon the earlier effectively filed date of the reference, it constitutes prior art under 35 U.S.C. 102(a)(1).
Regarding claim 8, the rejection of claim 7 is incorporated, furthermore MENARD teaches:
The method of claim 7, wherein generating the natural language letter comprises: generating an initial template based on a model of the plurality of models related to successful previous appeals;
“ This disclosure describes embodiments of systems and methods that may be used to apply artificial intelligence and/or machine learning to identify and correct problems with claims and to help providers conduct automated decisioning and submit claims appeals for denied claims. In some embodiments, claims and remittance data may be collected from a plurality of providers including hospitals, medical groups, doctors, and/or other clinicians. This data may, in some embodiments, be used to train one or more artificial intelligence or machine learning models to recognize claims that are likely to be denied as to a specific set of payer systems and to generate one or more reason codes or decisioning tools to reduce denials. In some embodiments, aggregating claims and remittance data across a plurality of providers may allow for more accurate and fine-grained predictions (for example, aggregating data means that more combinations of procedures, policies, and so forth., are included in the data). In some embodiments, one or more systems may provide a denial probability and/or one or more predicted Claim Adjustment Reason Codes (CARCs) and/or Remittance Advice Remark Codes (RARCs). One or more of the systems may generate electronic flags or notifications of claims with a high probability of denial prior to submission. Provider systems may use said codes to generate instructions for intervening or modifying the claim prior to electronically submitting claims to the payer systems, thereby reducing the likelihood that the claims are denied. ” (MENARD [0032])
MENARD in view of BURGESS does not teach but PRIESTAS teach:
And composing the letter based on the initial template, the summary of the extracted information, and one or more predefined policies related to appeal processes.
“ The document processing system 100 processes the message 104 and/or the documents 106 to extract data 108 required for the execution of the automated document processing task specified by the request 102. If the automated document processing task pertains to processing of a workers' compensation or casualty insurance claim, the document processing system 100 can analyze the information from the request 102 and one or more external data sources 150 to generate a recommendation 140 on whether or not the claim can be approved. The external data sources 150 can include information regarding the various policies in implementation, the policy holders, the requirements associated with the policies, and the historical transaction data of the various policy holders, etc. ... ” (PRIESTAS [0022])
“...If the automated document processing task relates to a provider denial of a claim, the output 114 may additionally include an automatically generated letter 116 which appeals the denial to the provider along with the requisite documentation. In an example, the documentation accompanying the letter 116 may include documents extracted from the request 102 or documents obtained from the external data sources 150. Output 114 can include other types of data and/or information based on a given configuration of system 100. ” (PRIESTAS [0023])
It would have been obvious to someone of ordinary skill in the art before the effective filling date of the claimed invention to include in the teachings of MENARD in view of BURGESS the capability to generate letters based on the record to describe the claim using natural language in order to appeal a denial decision from a responsible entity. The benefit and motivation of such modification is discussed by PRIESTAS in the following portion: “ The AI-based automatic document processing system disclosed herein provides for a technical improvement by enabling more accurate data extraction, as compared to conventional techniques, thereby providing better process automation. Many process automation systems receive certain data inputs, analyze the received data and produce certain outputs or automatically execute certain tasks based on the analyses of the received inputs. The automatically executed tasks can include, but are not limited to, generating recommendations or automatically sending out certain notifications or communications to preconfigured parties, etc. In the AI-based document processing system disclosed herein, the automatically executed tasks also include automatically generating letters, such as, appeal letters for provider denials. As the output that is generated depends on the data inputs provided, greater accuracy of the data inputs ensures more accurate outputs. ” (PRIESTAS [0020])
MENARD in view of BURGESS in view of PRIESTAS does not teach, but HASAN teaches:
composing a summary of the extracted information;
“ In an example, the member profile engine 181 may generate a profile summary 310 based on the data 305. The profile summary 310 may be separate from or included in the member profile. ” (HASAN [0134])
It would have been obvious to someone of ordinary skill in the art before the effective filling date of the claimed invention to include in the teachings of MENARD in view of BURGESS on further view of PRIESTAS the capability to compose a summary using natural language. The benefit and motivation of such modification is discussed by PRIESTAS in the following portion: “In some aspects, the healthcare system may support generating a health summary and sending the health summary to providers, so that the providers can engage the members on behalf of the healthcare system. Aspects described herein support a selection process on who to send the summary to (e.g., which providers receive the health summary).” (HASAN [0049])
MENARD in view of BURGESS in view of PRIESTAS in view of HASAN does not teach, but SCHOUTEN teaches:
decomposing the initial template into a plurality of prompts, each prompt of the plurality of prompts related to a sub-step of the appeal process;
“ So, referring to the healthcare records example used herein, a template 470 can be defined for conducting a dynamic query session when one or more records are found to have a balance exceeding a pre-defined threshold for longer than a pre-defined period of time, which can be defined in a rule 410 associated with that template 470. The template 470 can further define questions to be answered by the dynamic query session when executed by the annotation engine 460. Some of these questions, such as the account number, current balance, payor or responsible entity, etc., can be directly and automatically answered by the annotation engine 460 by querying the records 405. Other questions, such as a reason for the delay in payment and an estimate of when payment will be made, may be presented to a user through the notes user interface 465. The rule associated with the template can initiate actions such as requiring or enforcing a status update on the date payment is expected, initiating a communication such as a letter or email to one or more users of the records processing and management system 305 and/or responsible entity system 320, launching a workflow 450, or any other of a variety of actions that can be contemplated. ” (SCHOUTEN [0049])
extracting information related to each sub-step of the appeal process using the plurality of prompts;
“ According to one embodiment, the records management and processing system 305 can be further adapter to dynamically determine and execute actions customized to a particular client system, such as one or the service provider systems 315A, based on results of executing the dynamic query session. More specifically, data collected as a result of the dynamic query session can be stored in a table 475 by the annotation engine 460 of the records management and processing system 305 while or after conducting a dynamic query session. Based on this data, actions can be dynamically determined and taken directed to the further processing of one or more records for which the condition triggering the dynamic query session was detected. As noted, the actions to be taken, as well as an order of operations for those actions, can be determined based in part on the service provider for the record. ” (SCHOUTEN [0049])
It would have been obvious to someone of ordinary skill in the art before the effective filling date of the claimed invention to include in the teachings of MENARD in view of BURGESS in view of PRIESTAS in further view of HASAN the capability to generate prompts using natural language to obtain more information about the record. The benefit and motivation of such modification is discussed by PRIESTAS in the following portion: “ Data collected as a result of the dynamic query session can be stored 925 in a table. Based on this data, actions can be dynamically determined 930 and taken directed to the further processing of one or more records for which the condition was detected. More specifically, the actions to be taken can be determined 930 based in part on the service provider for the record. An order of operations for the actions can also be determined 930 based on the service provider for the record. ” (SCHOUTEN [0076])
Regarding claim 18, the rejection of claim 17 is incorporated, furthermore arguments analogous to claim 8 are applicable.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to HECTOR J. CRESPO FEBLES whose telephone number is (571)272-4512. The examiner can normally be reached Mon - Fri 7:30 - 5:00.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Daniel Washburn can be reached at (571) 272-5551. 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.
/HECTOR J. CRESPO FEBLES/Examiner, Art Unit 2657
/DANIEL C WASHBURN/Supervisory Patent Examiner, Art Unit 2657
Prosecution Insights