Prosecution Insights
Last updated: April 19, 2026
Application No. 18/387,794

USING LARGE LANGUAGE MODELS TO TEST THE VALIDITY OF A USER ACTION IN TREATMENT PLANNING

Non-Final OA §101§112
Filed
Nov 07, 2023
Examiner
SANGHERA, STEVEN G.S.
Art Unit
3684
Tech Center
3600 — Transportation & Electronic Commerce
Assignee
Siemens Healthineers International AG
OA Round
3 (Non-Final)
30%
Grant Probability
At Risk
3-4
OA Rounds
4y 6m
To Grant
60%
With Interview

Examiner Intelligence

Grants only 30% of cases
30%
Career Allow Rate
49 granted / 165 resolved
-22.3% vs TC avg
Strong +30% interview lift
Without
With
+30.4%
Interview Lift
resolved cases with interview
Typical timeline
4y 6m
Avg Prosecution
60 currently pending
Career history
225
Total Applications
across all art units

Statute-Specific Performance

§101
34.2%
-5.8% vs TC avg
§103
40.4%
+0.4% vs TC avg
§102
5.9%
-34.1% vs TC avg
§112
17.7%
-22.3% vs TC avg
Black line = Tech Center average estimate • Based on career data from 165 resolved cases

Office Action

§101 §112
DETAILED ACTION Continued Examination Under 37 CFR 1.114 A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 01/02/2026 has been entered. 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 . Response to Amendment In light of the amendments, the claims are rejected under 35 U.S.C. 112(a). In light of the amendments, the claims are rejected under 35 U.S.C. 112(b). In light of the amendments, the claims are rejected under 35 U.S.C. 101. In light of the amendments, the previous 35 U.S.C. 103 rejections have been withdrawn. Notice to Applicant In the amendment dated 01/02/2026, the following has occurred: claims 1, 6, 8, 13, 15, and 20 have been amended; claims 4, 11, and 18 are canceled; claims 2-3, 5, 7, 9-10, 12, 14, 16-17, and 19 remain unchanged; and no new claims have been added. Claims 1-3, 5-10, 12-17, and 19-20 are pending. Effective Filing Date: 11/07/2023 Response to Arguments 35 U.S.C. 101 Rejections: Applicant argues that none of these claim steps recite an abstract idea. Examiner however respectfully disagrees. The claims recite an abstract idea categorized under both certain methods of organizing human activity and mathematical concepts. The training step in particular is math, while the bulk of the remaining independent claim is directed to a person messaging another person for information. Applicant further states the claims recite a specific logical and structural sequence that improves the functioning of a large language model in the radiotherapy planning context and also cites the Ex Parte Desjardin decision. Examiner however respectfully disagrees that there is an improvement to the functioning of the LLM as the functionality of the LLM is not being changed, only the data that is being fed to it. The LLM is being used in its normal capacity. See also MPEP 2106.05(a)(I). The Recentive Analytics, Inc. v. Fox Corp. decision is directed to an ineligibility analysis rather than an eligibility test. Recentive held that non-specifically claimed training of an [AI/ML] algorithm is insufficient to provide a practical application or significantly more because it does not result in “improving the mathematical algorithm or making machine learning better.” Recentive at 12. The decision further instructed that “[i]terative training using selected training material…are incident to the very nature of machine learning” and thus does not provide for an improvement. Recentive at 12. Lastly, Applicant states that the claims are patent eligible as they provide “integral use of a machine to achieve performance of a method [to] integrate [any] recited judicial exception into a practical application or provide significantly more, in contrast to where the machine is merely an object on which the method operates, which does not integrate the exception into a practical application or provide significantly more.” Applicant further states that the method could not be performed with the integral use of these particular machine-implemented models and specialized data flows. As stated above, the claims recite an abstract idea which is being implemented using the particular machine-implemented models in an “apply it”, potentially even general linking, manner. 35 U.S.C. 103 Rejections: Examiner withdraws the previous 103 claim rejections in view of the amendments to the claims. Claim Rejections - 35 USC § 112(a) The following is a quotation of the first paragraph of 35 U.S.C. 112(a): (a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention. The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112: The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention. Claims 1-3, 5-10, 12-17, and 19-20 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention. Claims 1, 8, and 15 recite a “creating” step that involves the usage of a processor. Is a person creating this prompt using a processor? Or is the processor actually creating this prompt on its own? The specification does not outline how the processor itself creates this prompt leading Examiner to question whether Applicant had possession over the claimed invention at the time of filing. Claims 2-3, 5-7, 9-10, 12-14, 16-17, and 19-20 are rejected based on their dependency on the independent claims. Claim Rejections - 35 USC § 112(b) The following is a quotation of 35 U.S.C. 112(b): (b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention. The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph: The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention. Claims 1-3, 5-10, 12-17, and 19-20 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention. Claims 1, 8, and 15 recite the limitation “the radiation therapy plan optimizer computer model” in “responsive to receiving” step of each claim. There is insufficient antecedent basis for this limitation in the claim. Claims 2-3, 5-7, 9-10, 12-14, 16-17, and 19-20 are rejected based on their dependency on the independent claims. 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 1-3, 5-10, 12-17, and 19-20 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. Claims 1-3 and 5-7 are drawn to a method and claims 8-10, 12-17, and 19-20 are drawn to systems, each of which is within the four statutory categories. Claims 1-3, 5-10, 12-17, and 19-20 are further directed to an abstract idea on the grounds set out in detail below. As discussed below, the claims do not include additional elements that are sufficient to amount to significantly more than the abstract idea because the additional computer elements, which are recited at a high level of generality, provide conventional computer functions that do not add meaningful limits to practicing the abstract idea (Step 1: YES). Step 2A: Prong One: Claim 1 recites a method comprising: 1) presenting, by a1) a processor, b) a user interface providing an interaction interface between a plurality of medical professionals communicating regarding a radiation therapy treatment of a patient during a tumor board meeting or a radiotherapy treatment planning process; 2) receiving, by a1) the processor through the interaction interface, a first input comprising a first patient attribute of the patient and a second input corresponding to the radiation therapy treatment of the patient; 3) creating, by a1) the processor, a prompt containing the first patient attribute of the patient and the radiation therapy treatment of the patient in a text format according to a prompt template stored c) in memory identifying specific locations to insert patient attributes and inputs corresponding to radiation therapy treatments within the prompt; 4) executing, by a1) the processor, d) a large language model using the created prompt to generate a text string of characters identifying a predicted task to be completed prior to generating a treatment plan for the patient generated using e) a treatment plan optimizer computer model, wherein d) the large language model is trained using text of a set of transcriptions of a set of tumor board meetings or radiotherapy treatment planning processes for a set of previously implemented radiation therapy treatments and a hierarchy of tasks associated with generating treatment plans; 5) presenting, by a1) the processor, the text string of characters identifying the predicted task for the treatment plan on the interaction interface; 6) receiving, by a1) the processor from the interaction interface, a third input containing text identifying an input task, and 7) when the text of the third input does not match the text of the predicted task: 7a) presenting, by a1) the processor on the interaction interface, an indication of the predicted task and an indication of a difference between the input task and the predicted task; 7b) responsive to receiving, from the interaction interface, an indication accepting the predicted task, transmitting, by a1) the processor, the first input, the second input and the predicted task to f) the radiation therapy plan optimizer computer model; and 7c) instructing, by a1) the processor, f) the radiation therapy plan optimizer computer model to generate the radiotherapy treatment plan for the patient using the first input, the second input, and the predicted task. Claim 1 recites, in part, performing the steps of 1) presenting a user interface providing an interaction interface (when a piece of paper) between a plurality of medical professionals communicating regarding a radiation therapy treatment of a patient during a tumor board meeting or a radiotherapy treatment planning process, 2) receiving, through the interaction interface, a first input comprising a first patient attribute of the patient and a second input corresponding to the radiation therapy treatment of the patient, 3) creating a prompt containing the first patient attribute of the patient and the radiation therapy treatment of the patient in a text format according to a prompt template stored in memory (mental storage of information on a piece of paper) identifying specific locations to insert patient attributes and inputs corresponding to radiation therapy treatments within the prompt, 5) presenting the text string of characters identifying the predicted task for the treatment plan on the interaction interface, 6) receiving, from the interaction interface, a third input containing text identifying an input task, and 7) when the text of the third input does not match the text of the predicted task: 7a) presenting, on the interaction interface, an indication of the predicted task and an indication of a difference between the input task and the predicted task, 7b) responsive to receiving, from the interaction interface, an indication accepting the predicted task, transmitting the first input, the second input and the predicted task to the radiation therapy plan optimizer model, and 7c) instructing the radiation therapy plan optimizer model to generate the radiotherapy treatment plan for the patient using the first input, the second input, and the predicted task. These steps correspond to Certain Methods of Organizing Human Activity, more particularly, managing personal behavior or relationships or interactions between people (including following rules or instructions). For example, the claims describe a process of determining the appropriate steps to treat a patient undergoing radiation therapy treatment, where an incorrect step is addressed. Claim 1 also recites, in part, the step of 4) executing a model using the created prompt to generate a text string of characters identifying a predicted task to be completed prior to generating a treatment plan for the patient generated using a treatment plan optimizer model, wherein the model is trained using text of a set of transcriptions of a set of tumor board meetings or radiotherapy treatment planning processes for a set of previously implemented radiation therapy treatments and a hierarchy of tasks associated with generating treatment plans. This step corresponds to Mathematical Concepts. The above limitations will be considered as a single abstract idea going forward. Independent claims 8 and 15 recite similar limitations and are also directed to an abstract idea under the same analysis. Depending claims 2-3, 5-7, 9-10, 12-14, 16-17, and 19-20 include all of the limitations of claims 1, 8, and 15, and therefore likewise incorporate the above described abstract idea. Depending claims 2, 9, and 16 add the additional steps of “executing, by the processor, an analytical protocol to identify a value for the predicted task” and “presenting, by the processor, the value for the predicted task on the interaction interface”; claims 5, 12, and 19 add the additional step of “presenting, by the processor on the interaction interface, a hyperlink configured to direct the interaction interface to third-party data associated with the predicted task”; claims 6, 13, and 20 add the additional steps of “receiving, by the processor, a response to presentation of the predicted task” and “retraining, by the processor, the large language model using the response”; and claims 7 and 14 add the additional step of “generating, by the processor, an alternative workflow that does not include the predicted task”. Additionally, the limitations of depending claims 3, 10, and 17 further specify elements from the claims from which they depend on without adding any additional steps. These additional limitations only further serve to limit the abstract idea. Thus, depending claims 2-3, 5-7, 9-10, 12-14, 16-17, and 19-20 are nonetheless directed towards fundamentally the same abstract idea as independent claims 1, 8, and 15 (Step 2A (Prong One): YES). Prong Two: This judicial exception is not integrated into a practical application. In particular, the claims recite the additional elements of – using a) a server (from claims 8 and 15) comprising a1) a processor (from claims 1, 8, and 15) and a2) a non-transitory computer-readable medium containing instructions that when executed by the processor causes the processor to perform functions (from claim 15), b) a user interface providing an interaction interface (when a computer display), c) memory, d) a large language model, e) a treatment plan optimizer computer model, f) the radiation therapy plan optimizer computer model, and g) a computer configured to display a user interface (from claim 15) to perform the claimed steps. The a) server comprising a1) a processor and a2) a non-transitory computer-readable medium containing instructions that when executed by the processor causes the processor to perform functions, b) user interface providing an interaction interface, c) memory, e) treatment plan optimizer computer model, f) radiation therapy plan optimizer computer model, and g) computer configured to display a user interface in these steps are recited at a high-level of generality (i.e., as generic components performing generic computer functions) such that it amount to no more than mere instructions to apply the exception using generic computer components, see MPEP 2106.05(f). The d) large language model processing model in these steps are recited at a high-level of generality (i.e., as generic components performing generic computer functions) such that it amount to no more than mere instructions to apply the exception using generic computer components (see: Applicant’s specification, paragraph [0006] where there is a generic processing model, see MPEP 2106.05(f)). Dependent claims recite additional subject matter which amount to limitations consistent with the additional elements in the independent claims. 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. Accordingly, these additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. The claims are directed to an abstract idea (Step 2A (Prong Two): NO). Step 2B: The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional elements of using a) a server comprising a1) a processor and a2) a non-transitory computer-readable medium containing instructions that when executed by the processor causes the processor to perform functions, b) a user interface providing an interaction interface, c) memory, d) a large language model, e) a treatment plan optimizer computer model, f) the radiation therapy plan optimizer computer model, and g) a computer configured to display a user interface to perform the claimed steps amounts to no more than insignificant extra-solution activity in the form of WURC activity (well-understood, routine, and conventional activity), a general linking to a particular technological field, or mere instructions to apply the exception using a generic computer component that does not offer “significantly more” than the abstract idea itself because the claims do not recite an improvement to another technology or technical field, an improvement to the functioning of any computer itself, or provide meaningful limitations beyond generally linking an abstract idea to a particular technological environment. It should be noted that the claims do not include additional elements that amount to significantly more than the judicial exception because the Specification recites mere generic computer components, as discussed above that are being used to apply certain mental steps, certain method steps of organizing human activity, or certain mathematical steps. Specifically, MPEP 2106.05(f) recites that the following limitations are not significantly more: Adding the words "apply it" (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, e.g., a limitation indicating that a particular function such as creating and maintaining electronic records is performed by a computer, as discussed in Alice Corp., 134 S. Ct. at 2360, 110 USPQ2d at 1984 (see MPEP § 2106.05(f)). The current invention generates a predicted task using a) a server comprising a1) a processor and a2) a non-transitory computer-readable medium containing instructions that when executed by the processor causes the processor to perform functions, b) a user interface providing an interaction interface, c) memory, d) a large language model, e) a treatment plan optimizer computer model, f) the radiation therapy plan optimizer computer model, and g) a computer configured to display a user interface, thus these components are adding the words “apply it” with mere instructions to implement the abstract idea on a computer. Mere instructions to apply an exception using generic computer components cannot provide an inventive concept. The claims are not patent eligible (Step 2B: NO). Claims 1-3, 5-10, 12-17, and 19-20 are therefore rejected under 35 U.S.C. 101 as being directed to non-statutory subject matter. Conclusion Any inquiry concerning this communication or earlier communications from the examiner should be directed to Steven G.S. Sanghera whose telephone number is (571)272-6873. The examiner can normally be reached M-F 7:30-5:00 (alternating Fri). 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, Shahid Merchant can be reached on 571-270-1360. 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. /STEVEN G.S. SANGHERA/Primary Examiner, Art Unit 3684
Read full office action

Prosecution Timeline

Nov 07, 2023
Application Filed
Apr 15, 2025
Non-Final Rejection — §101, §112
Jun 20, 2025
Applicant Interview (Telephonic)
Jun 20, 2025
Examiner Interview Summary
Jul 18, 2025
Response Filed
Oct 01, 2025
Final Rejection — §101, §112
Jan 02, 2026
Request for Continued Examination
Feb 12, 2026
Response after Non-Final Action
Mar 11, 2026
Non-Final Rejection — §101, §112 (current)

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12573497
SYSTEMS AND METHODS FOR AUTOMATING WORKFLOWS
2y 5m to grant Granted Mar 10, 2026
Patent 12558015
ENHANCED COMPUTATIONAL HEART SIMULATIONS
2y 5m to grant Granted Feb 24, 2026
Patent 12551170
PROVIDING A VISUAL REPRESENTATION OF PATIENT MONITORING DATA
2y 5m to grant Granted Feb 17, 2026
Patent 12469583
SYSTEM AND METHOD FOR PROCESSING PATIENT-RELATED MEDICAL DATA
2y 5m to grant Granted Nov 11, 2025
Patent 12437870
GENERATION OF DATASETS FOR MACHINE LEARNING MODELS AND AUTOMATED PREDICTIVE MODELING OF OCULAR SURFACE DISEASE
2y 5m to grant Granted Oct 07, 2025
Study what changed to get past this examiner. Based on 5 most recent grants.

AI Strategy Recommendation

Get an AI-powered prosecution strategy using examiner precedents, rejection analysis, and claim mapping.
Powered by AI — typically takes 5-10 seconds

Prosecution Projections

3-4
Expected OA Rounds
30%
Grant Probability
60%
With Interview (+30.4%)
4y 6m
Median Time to Grant
High
PTA Risk
Based on 165 resolved cases by this examiner. Grant probability derived from career allow rate.

Sign in with your work email

Enter your email to receive a magic link. No password needed.

Personal email addresses (Gmail, Yahoo, etc.) are not accepted.

Free tier: 3 strategy analyses per month