DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Status of the Claims
The office action is in response to the claim remarks filed on May 19, 2026 for the application filed February 9, 2023. Claims 1, 9, 10-15, 22 and 24-28 are currently pending and have been examined.
Withdrawal of Finality of Last Office Action
Applicant’s request for reconsideration of the finality of the rejection of the last Office action is persuasive and, therefore, the finality of that action is withdrawn.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
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, 9, 10-15, 22 and 24-28 are rejected under 35 U.S.C. 103 as being unpatentable over Hegselmann et al. (TabLLM: Few-shot Classification of Tabular Data with Large Language Models) in view of Wang et al. (SurvTRACE: Transformers for Survival Analysis with Competing Events), herein after “SurvTRACE”.
Regarding claim 1, Hegselmann discloses a computer-implemented method executed on data processing hardware that causes the data processing hardware to perform operations comprising (The methods disclosed by Hegselmann are construed as computer-implemented and executed on data processing hardware that causes the data processing hardware to perform operations.):
receiving a clinical data table for a patient, the clinical data table storing clinical data associated with the patient in tabular form (Page 2 and Fig. 1 and Page 3 Table 3. Show receiving a tabular dataset which include clinical data associated with a patient. Also see page 5 section 4.4, Each patient record is a time series of visits, with each visit consisting of a list of medical conditions and procedures.);
extracting, from the clinical data table, one or more categorical features and one or more continuous features (Page 3, section 3.1, Problem Formalization, Suppose we have a tabular dataset with 𝑛 rows and 𝑑 columns or features. We can formalize this as 𝐷 x𝑖 𝑦𝑖 𝑛 𝑖 1, where each x𝑖 is a 𝑑 dimensional feature vector. Since we consider classification, 𝑦𝑖 for a set of classes 𝐶. We define the column names or feature names as F= {f1… 𝑓𝑑} . We assume the 𝑓𝑖’s are natural-language strings such as “age” or “education” (see Figure 1). Also see page 3 section 2.1, Serialization of Tabular Data. Fig. 1 shows that the features may be categorical or continuous.).;
serializing the one or more categorical features and the one or more continuous features extracted from the clinical data table into an input text sequence by applying a serialization template to each feature to produce a sequence of natural langue tokens (Page3, section 3.1, To use an LLM for tab ular data, the table must be transformed into a natural text representation. Typically, when prompting an LLM, there is a template used to both serialize the inputs into one natural-language string, and to provide the prompt itself (e.g., the string “Does this person make more than 50,000 dollars? Yes or no?”), which is usually located after the serialized input. In this work, we break these pieces up into a serialization and a prompt. We define a function serialize𝐹x that takes the column names 𝐹 and feature values x for a row as inputs and creates a textual representation of the input. Combining this serialization with a task-specific prompt 𝑝 will then form the LLM input serialize𝐹x 𝑝. Also see Page 3, section 3.2 and page 21, section 8.),
determining, using a clinical prediction model comprising a large language model, one or more predicted clinical outcomes for the patient by processing, using the large language model, the input text sequence to generate the one or more predicted clinical outcomes (Page 3, section 3.1, Large Language Models For Classification, TabLLM can be used with different LLMs that generate text based on a natural-language input. Let LLM be an LLM with vocabulary 𝑉. Then, LLM serialize𝐹x 𝑝 𝑉 is the prompted output of the LLM. Page 21, section shows the prediction tasks/prompts can include clinical outcome predicitons, such as “does this patient die in the next nine months”. Also see fig. 1.); and
Wang does not appear to explicitly disclose providing, for output from a client device associated with a user, the one or more predicted clinical outcomes for the patient.
SurvTRACE teaches that it was old and well known in the art of clinical prediction at the time of the filing to provide, for output from a client device associated with a user, the one or more predicted clinical outcomes for the patient (SurvTRACE, Page 6, Figure 5 and section 5.4.3 show and discuss providing visualizations to a user showing predicted outcomes, such overall survival, construed as for output to a device.) to provide a case-by-case explanation for each individual (SurvTRACE, Page 6, section 6).
Therefore, it would have been obvious to one of ordinary skill in the art of clinical prediction at the time of the filing to modify the method of Hegselmann to include providing, for output from a client device associated with a user, the one or more predicted clinical outcomes for the patient, as taught by SurvTRACE, in order to provide a case-by-case explanation for each individual.
Regarding claim 8, Hegselmann further discloses wherein the clinical prediction model executes on the data processing hardware (LLM’s operate on data processing hardware ).
Regarding claim 10, Hegselmann further discloses wherein the large language model comprises a pre-trained large language model and is fine-tuned using few-shot learning (Page 1, section 1, Introduction, large language models (LLMs) such as GPT-3, which are pre-trained. In this work we introduce TabLLM, which is a general framework to leverage LLMs for few-shot classification of tabular data.).
Regarding claim 11, Hegselmann further discloses wherein the large language model comprises a domain-specific large language model pre-trained on a vocabulary and/or syntax associated with particular domain (Page 3, section 3.2, Text T0: We use the LLM T0 with 11B parameters (bigscience/T0pp) (Sanh et al., 2022). Page 8, section 6, Discussion, medical-domain-specific language models, such as PubMedBERT, and general-domain models with medical data in their training sets, such as GPT 3, perform well at downstream prediction tasks on medical data. Substituting T0 with one of these models in TabLLM is an interesting direction for future work.).
Regarding claim 12, Hegselmann further discloses wherein the particular domain comprises medical terminology (Page 8, section 6, Discussion, medical-domain-specific language models, such as PubMedBERT).
Regarding claim 13, Hegselmann does not appear to explicitly disclose, but SurvTRACE teaches that it was old and well known in the art of clinical prediction at the time of the filing wherein the one or more predicted clinical outcomes comprise at least one of overall survival, progression-free survival, or a best overall response (SurvTRACE, Page 7, Figure 5) to provide a case-by-case explanation for each individual (SurvTRACE, Page 6, section 6).
Therefore, it would have been obvious to one of ordinary skill in the art of clinical prediction at the time of the filing to modify the method of Hegselmann such that the one or more predicted clinical outcomes comprise at least one of overall survival, progression-free survival, or a best overall response, as taught by SurvTRACE, in order to provide a case-by-case explanation for each individual.
Regarding claim 14, Hegselmann does not appear to explicitly disclose, but SurvTRACE teaches that it was old and well known in the art of clinical prediction at the time of the filing wherein the one or more predicted clinical outcomes comprises at least one of a recommended treatment or a prognostic biomarker score (SurvTRACE, Page 2, section 1, (2), we inspect how the learned attention scores demonstrate relevance between covariates as well as show interpretability for the prediction results. Page 7, Figure 4, Visualization of attention scores between covariates for two patients; MKI67, EGFR, PGR, ERB2,and ER, are gene biomarkers; HT: Hormone treatment; RT: Radiotherapy; CT: Chemotherapy; ER_P: ER Positive. Also see Page 7, section 5.4.2.).
Therefore, it would have been obvious to one of ordinary skill in the art of clinical prediction at the time of the filing to modify the method of Hegselmann such that the one or more predicted clinical outcomes comprises at least one of a recommended treatment or a prognostic biomarker score, as taught by SurvTRACE, in order to provide a case-by-case explanation for each individual.
Regarding claims 15, 22 and 24-28: all limitations as recited have been analyzed and rejected with respect to claims 1, 8 and 10-14. Claims 15, 22 and 24-28 pertain to a system, corresponding to the method of claims 1, 8 and 10-14. Claims 15, 22 and 24-28 do not teach or define any new limitations beyond claims 1, 8 and 10-14; therefore claims 15, 22 and 24-28 are rejected under the same rationale.
Response to Arguments
Applicant's arguments filed May 19, 2026, with respect to claims 1, 8, 10-15, 22 and 24-28 being rejected under 35 U.S.C. §103 have been fully considered but are moot in view of the new grounds of rejection.
Conclusion
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 Devin C. Hein whose telephone number is (303)297-4305. The examiner can normally be reached 9:00 AM - 5:00 PM M-F MDT.
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, Jason B. Dunham can be reached at (571) 272-8109. 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.
/DEVIN C HEIN/Examiner, Art Unit 3686
Prosecution Insights