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 .
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.
Response to Amendment
In the amendment dated 4/2/2026, the following has occurred: Claims 1 – 6, 8 – 13, 15 – 20 have been amended; Claims 21 – 25 have been added.
Claims 1 – 25 are pending.
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 – 25 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more.
The claims, understood as a whole, recites subject matter within a statutory category as a process (claims 8 – 14), machine (claims 15 – 20), and manufacture (claims 1 – 7 and 21 – 25) which recite the abstract idea steps of
receiving medical notation data for a target patient corresponding to at least one of: (a) a discussion between a physician and a patient, or (b) a physician-generated medical diagnosis of the patient;
partitioning the medical notation data into a plurality of sequences of tokens, wherein the tokens in the plurality of sequences of tokens correspond at least to words in the medical notation data;
generating, for the plurality of sequences of tokens, a plurality of per-code output values corresponding to a plurality of classification codes, wherein generating the plurality of per-code output values comprises:
for a first sequence of the plurality of sequences: applying algorithms that generate an embedding from the first sequence and a first set of per-code output values corresponding to the plurality of classification codes;
determining a plurality of composite classification values for the plurality of classification codes, at least by:
for a first classification code of the plurality of classification codes a first composite classification value for the target patient associated with the first classification code by processing a second set of per-code output values for the first classification code across the plurality of sequences;
based on plurality of composite classification values determined for the plurality of classification codes, selecting the first classification code of the plurality of classification codes as a predicted classification code for the target patient; and
storing the predicted classification code for the target patient.
The Examiner understands the claimed invention, as a whole, in light of the Specification. The Examiner is therefore bound by what the Specification states. For example, the Specification describes the use of existing technology applied to the abstract idea to obtain all the benefits of applying the abstract idea to technology. There is nothing disclosed in the specification that describes the invention as a technical improvement or a technological improvement to overcome a technical problem.
The problem is disclosed in paragraph 3 as overcoming human, manual operations. As stated in paragraph 3
[3] The DRGs are a patient classification scheme that provides a means of relating the type of patients a hospital treats reflected as a case mix to the costs incurred by the hospital. The introduction of DRGs in prospective payment systems has put pressure on hospitals to optimize cost and quality with efficient resource utilization. DRG-based statistics are reviewed by hospital managers to assess its patient mix and financial efficiency under DRG reimbursement. Hospitals allocate experts for the manual calculation of DRG. This is a time-consuming process. Since DRGs are conventionally obtained post-discharge, this makes it impossible for hospitals to act upon such vital information about DRG and potential spending on care for active patients and claim a reimbursement in case of over-spending. Hence, hospitals need a streamlined process that requires accurate coding and could aid in improving cost estimates and resource allocation.
Therefore, the invention uses technology such as a machine learning algorithm. However, the invention is not directed towards technology, such as a new machine learning algorithm.
These steps of claims 1 – 25, as drafted, under the broadest reasonable interpretation, includes mathematical concepts. Figure 2 describes the inventions claimed mathematical steps as:
PNG
media_image1.png
988
576
media_image1.png
Greyscale
These mathematical steps are further emphasized throughout the Specification. In particular, paragraph 41 includes,
For example, the machine learning model 114 generates a first set of probability values for a set of medical billing classification codes based on a first sequence of tokens generated based on the medical notation data 141. The machine learning model 114 generates a second set of probability values for the same set of medical billing classification codes based on a second sequence of tokens generated based on the same medical notation data 141. The machine learning model 114 may generate a third set of probability values for the same set of medical billing classification codes based on a third sequence of tokens generated based on the same medical notation data 141. The medical billing classification code selection engine 115 applies a mathematical or logical algorithm to the sets of probability values for the set of sequences associated with the medical notation data 141 to select a particular predicted medical billing classification code for the medical notation data 141. The mathematical or logical algorithm may include one or more of the following:
The Examiner believes that the invention’s claimed mathematical steps are used to better organize human activity.
These steps of claims 1 – 25, as drafted, under the broadest reasonable interpretation, includes methods of organizing human activity. As mentioned above with the paragraph 3 citation, the invention is directed towards reducing manual errors and therefore reducing medical costs. The Specification in paragraphs 78 – 90, “4. EXAMPLE EMBODIMENT” describes the results of the claimed invention
[90] The healthcare provider uses the medical billing prediction, generated from the DRG classification code prediction based on the medical notation data 402a from the 12 hours after a patient checked in, to predict longer-term billing for the patient and generate or modify components of a treatment plan for the patient.
Therefore, based upon the plain reading the claimed invention in light of the Specification, the claimed invention is directed towards medical billing transactions.
Dependent claims recite additional subject matter which further narrows or defines the abstract idea embodied in the claims (such as claims 2 – 7, 9 – 14, and 16 – 25, reciting particular aspects of how math may be performed but for recitation of generic computer components).
This judicial exception is not integrated into a practical application. In particular, the additional elements do not integrate the abstract idea into a practical application, other than the abstract idea per se, because the additional elements amount to no more than limitations which:
amount to mere instructions to apply an exception (such as recitation of by a server amounts to invoking computers as a tool to perform the abstract idea, see MPEP 2106.05(f))
add insignificant extra-solution activity to the abstract idea (such as recitation of receiving medical notation data amounts to mere data gathering, recitation of storing predicted amounts to insignificant application, see MPEP 2106.05(g))
Dependent claims recite additional subject matter which amount to limitations consistent with the additional elements in the independent claims (such as claims 2 – 7, 9 – 14, and 16 – 25, additional limitations which amount to invoking computers as a tool to perform the abstract idea). Looking at the limitations as an ordered combination adds nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer or improves any other technology. Their collective functions merely provide conventional computer implementation and do not impose a meaningful limit to integrate the abstract idea into a practical application.
The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to discussion of integration of the abstract idea into a practical application, the additional elements amount to no more than mere instructions to apply an exception, add insignificant extra-solution activity to the abstract idea, and generally link the abstract idea to a particular technological environment or field of use. Additionally, the additional limitations, other than the abstract idea per se, amount to no more than limitations which:
amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields (such as claims 1 – 25; partitioning, applying a trained machine learning model, and selecting e.g., performing repetitive calculations, Flook, MPEP 2106.05(d)(II)(ii))
Additional Elements
Computer or digital device 110 -paragraph 27 any hardware device that includes a processor.
Computer readable media – paragraph 105 - any non-transitory media that store data and/or instructions that cause a machine to operate in a specific fashion.
Network – paragraph 96 internet
Client interface – paragraph 96 web browser
Machine learning model – paragraphs 38 – 40 including a foundation model (paragraph 38) and a classification head (paragraphs 37, 62, and 71) neural network layers
Large language model – paragraph 28, 30, and 40
Token – paragraph 32 token is a set of one or more characters that are grouped together
Classification code – paragraph 13 medical billing classification codes may be, for example, Diagnosis-Related Groups (DRGs). Paragraph 2 According to the Centers for Medicare and Medicaid Services (CMS), each DRG has a fixed payment rate based on the average cost of resources used to treat a specific diagnosis category. The DRGs were developed to enable an effective framework that would improve the efficiency of procedures and treatments for patients with the same disease category, thereby standardizing the costs without degrading the quality of care given to the patient.
Selection engine – paragraph 4 applies a mathematical or logical algorithm to the sets of probability values for the set of sequences associated with the medical notation data
Dependent claims recite additional subject matter which, as discussed above with respect to integration of the abstract idea into a practical application, amount to invoking computers as a tool to perform the abstract idea. Dependent claims recite additional subject matter which amount to limitations consistent with the additional elements in the independent claims (such as claims 2 – 7, 9 – 14, and 16 – 25, additional limitations which amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields, partitioning, computing the probability, predicting, training, , e.g., performing repetitive calculations, Flook, MPEP 2106.05(d)(II)(ii)). Looking at the limitations as an ordered combination adds nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer or improves any other technology. Their collective functions merely provide conventional computer implementation.
Response to Arguments
Applicant's arguments filed 4/2/2026 have been fully considered but they are not persuasive.
Rejections under 35 U.S.C. § 101
I. Step 2A, Prong 1: The claims do not recite an abstract idea
The claims do not recite any mathematical concepts.
The Applicant states, “Claims 1, 8, and 15 recite no mathematical relationship between variables, no formula or equation, and no mathematical calculation expressed in words or symbols (MPEP 2106.04(a)(2)).” The Examiner repeats from the Interview that subsection C does not require explicit words as asserted.
The Applicant states, “Here, the Examiner has expressly important content from the specification into the claims, where the claims do not recite the content from the specification. This is clearly improper under MPEP 2106.04(a)(2) and MPEP 2111.01(11).” The Applicant was free to express how the claimed limitations are performed other than the disclosed mathematical algorithms. The claims are not required to express the algorithms that perform the steps but the Specification provides guidance on how those steps are performed. The MPEP 2106.04(a)(2)(C) discusses this in further.
The Applicant states, “Claims 1, 8, and 15 recite a novel improvement to a computer's ability to generate classification predictions by partitioning medical notation data into sequences of tokens and applying a machine learning model to the sequences to generate, for each sequence, a set of per-code output values for a set of classification codes.” The Examiner notes that this summary is a string of mathematical steps.
The Applicant states, “Instead, they describe operations of a machine learning model applied to token-bounded sequences of medical notation data.” Per USPTO guidance, a machine learning model is math.
The claims do not recite certain methods of organizing human activity.
The Applicant states, “Claims 1, 8, and 15 recite no billing transaction, no commercial interaction, no contract, no legal obligation, no payment, and no economic practice. In addition, the claims fail to recite any "medical billing transactions," as identified by the Examiner.” The Examiner understands the claimed invention, as a whole, in light of the Specification. The Examiner stands by the interpretation. The Applicant’s opinion differs.
The Applicant states, “The Examiner has pointed to no limitation in the claims that recites "medical billing transactions." Instead, the Examiner again improperly imports limitations from the specification that are not recited in the claims.” The Applicant has broadened the claims by changing “medical billing classification codes” to “classification codes.” However, the Specification provides no other classification codes besides medical billing classification codes.
The Applicant states, “Even if the claims did recite medical billing transactions, which they do not, "medical billing transactions" do not map onto any enumerated sub-grouping. Instead, claims 1, 8, and 15 are directed to processing medical notation data in a novel way to generate a prediction for a classification for a target patient.” Except for “the classification head,” the only use of classification within the Specification relates to medical billing classification codes.
For example, paragraph 2 includes: The Inpatient Prospective Payment System (IPPS) categorizes each inpatient hospital admission with similar clinical and treatment characteristics into a Diagnosis Related Group (DRG), where patients in the same group are expected to incur a similar cost from hospital resource utilization.”
The Specification continues with:
[89] The system provides the DRG classification code prediction 409 for the medical notation data 402a to a medical billing model 410 to generate a medical billing prediction 411 for a patient. The medical billing model 410 generates the prediction based on a formula that includes the following: the predicted DRG classification code, a standardized amount associated with the healthcare provider generating the medical notation data, a cost of living adjustment based on a geographic location of a healthcare provider, a patient's age, a number of diagnoses, a predicted length of stay, and if a healthcare provider is a teaching hospital.
[90] The healthcare provider uses the medical billing prediction, generated from the DRG classification code prediction based on the medical notation data 402a from the 12 hours after a patient checked in, to predict longer-term billing for the patient and generate or modify components of a treatment plan for the patient.
The Examiner is required to understand the claimed invention, as a whole, in light of the Specification. The Specification describes the invention directed towards patient medical billing. The Applicant provides no proof that the Examiner is mistaken.
II. Step 2A, Prong 2: The claims are not directed to an abstract idea
The Applicant states, “A system divides medical notation data into sequences of tokens and applies the machine learning model to each sequence to generate a respective sets of per-code output values for a set of classification codes. The system generates an overall prediction based on a combination of the per-code output values for the classification codes across the sequences of tokens.” The Applicant’s opinion is noted.
1. Claims 1, 8, and 15, When Considered as a Whole, Integrate Any Judicial Exception Into a Practical Application
A. The claims reflect an improvement to the functioning of a computer
The Applicant states, “This is an improvement to conventional prediction models that are
constrained by the input limits. As a result, conventional models are forced to somehow reduce the data provided to the prediction models to generate predictions, resulting in predictions that
are based on incomplete sets of data.” The Applicant’s opinion is noted. Further, the invention is not directed towards a technological improvement to overcome a problem of technology.
The Claims Reflect Improvements to Computational Performance
The Applicant states, “The specification describes this constraint that limits conventional predictive systems: a particular ML model may accept no more than 450 tokens as input, while a set of medical notation data may correspond to 4,000 tokens. See Specification, para. 15.” The Specification does not disclose that these limits are constraints. Paragraph 15 does not disclose how the limits are determined.
The Applicant states, “Claims 1, 8, and 15 address this computational constraint by partitioning the medical notation data into a plurality of token-limit-compatible sequences, applying the machine learning model to each sequence to generate per-sequence sets of output values for a plurality classification codes, and predicting an overall classification code based on the output values across all sequences.” The Applicant above creates a “constraint” that is not disclosed. The Applicant solves that new matter by applying a solution. The Examiner is constrained by the originally filed specification.
Any arguments directed towards a technological improvement are considered moot. The invention is not disclosed as being one.
The Claims Reflect Improvements to Data Storage
The Applicant states, “Without the claimed process, a system that cannot ingest medical notation data exceeding the model's token input limit must either store the unprocessed record indefinitely without generating a prediction or discard the record and lose the associated clinical data.” The Applicant’s opinion is noted. Paragraph 105 states, “Common forms of storage media include, for example, a floppy disk, a flexible disk, hard disk, solid state drive, magnetic tape, or any other magnetic data storage medium, a CD-ROM, any other optical data storage medium, any physical medium with patterns of holes, a RAM, a PROM, and EPROM, a FLASH-EPROM, NVRAM, any other memory chip or cartridge, content-addressable memory (CAM), and ternary content-addressable memory (TCAM).” The Examiner does not see the foundation for the Applicant’s opinion.
The Claims Reflect Improvements to Data Structures
The Applicant states, “The medical notation data, as received, is structurally incompatible with the model's input requirements.” The Applicant’s opinion is noted.
Improvements to the Performance of Computers Achieved by Multi-Sequence Partitioning and Cross-Sequence Output Aggregation for ML-Based Code Prediction Are Apparent to One of Ordinary Skill in the Art
Desjardins Applies to All Examination, Not Just to the Type of ML Model Described in Desjardins
The Applicant states, “Similar to Desjardins, the claims here are directed to the application of a machine learning model to generate predictions.” The Desjardins opinion relates to a machine learning result of technological improvement. As the Applicant is applying existing technology and does not disclose a technological improvement, Desjardins does not apply.
II. Step 2B: Claims 1, 8, and 15 Recite Additional Elements That, Individually and in Combination, Amount to Significantly More Than Any Judicial Exception
The Applicant states, “A claim is patent-eligible when it recites additional elements that, individually or in combination, amount to significantly more than a judicial exception.” The Examiner notes that MPEP 2106.05(II) includes, “Like the other steps in the eligibility analysis, evaluation of this step should be made after determining what the inventor has invented by reviewing the entire application disclosure and construing the claims in accordance with their broadest reasonable interpretation.” The Examiner has done so. The result of the invention is data that has a potential usage and therefore there is no practical application.
1. Additional Elements
The Applicant states, “In addition, the following elements are additional elements and are not abstract ideas:” The Applicant’s opinion as to what are additional elements is noted.
2. The Additional Elements, Individually and in Combination, Amount to Significantly More Than an Abstract Idea
i. The Claims Improve the Technology of ML-Based Prediction From Input-Constrained Models
The Applicant states, “Here, the claim recites a multi-sequence partitioning and cross-sequence output aggregation architecture that enables a token-input-limited ML model to generate classification code predictions from medical notation data that the model cannot otherwise ingest in a single pass.” Please see above regarding the Applicant’s additional language not found within the originally filed specification.
ii. The Claims Include Limitations That Are Not Well-Understood, Routine, or Conventional in the Field
The Applicant states, “A determination that a limitation is "well-understood, routine, or conventional" can only be made when the Examiner can readily conclude that the element or elements are widely prevalent or in common use in the relevant industry.” The Examiner goes by the MPEP and not the Applicant’s interpretation. The MPEP states, “Another consideration when determining whether a claim recites significantly more than a judicial exception is whether the additional element(s) are well-understood, routine, conventional activities previously known to the industry. This consideration is only evaluated in Step 2B of the eligibility analysis.” (emphasis added) The Examiner stands by the Specification’s disclosure of the additional elements and the Applicant does not provide proof that the Examiner is incorrect.
iii. The Claims Add Meaningful Limitations Beyond Generally Linking a Judicial Exception to a Particular Technological Environment
The Applicant states, “These characterizations apply only to the peripheral elements of the claim and do not address the substance of what the claim recites.” It is noted that the Applicant provides no quotation from the MPEP regarding the basis of his opinion. The Examiner relies upon the invention as disclosed.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Khotiilovich et al. Pub. No.: US 2023/0215552 predicting patient qualification for application of coordinated healthcare resources
Wu et al Pub. No.: US 2022/0319706 A DRGs automatic grouping method based on convolutional neural network
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Neal R Sereboff whose telephone number is (571)270-1373. The examiner can normally be reached M - T, M - F 8AM - 6PM.
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, Robert Morgan can be reached at (571)272-6773. 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.
/NEAL SEREBOFF/
Primary Examiner
Art Unit 3626
Prosecution Insights