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 Application
This action is in reply to the correspondence received through August 6, 2025.
Claims 2, 9, 16, 32, 35, and 37 are amended.
Claims 6, 13, 20, 26-30, 34, 36, and 39-51 are canceled.
Claims 1-5, 7-12, 14-19, 21-25, 31-33, 35, 37, and 38 are pending.
Information Disclosure Statement
The information disclosure statement submitted August 6, 2025 and its contents have been considered.
Claim Rejections - 35 U.S.C. § 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 15-19 and 21 are rejected under 35 U.S.C. § 101 because the claimed invention is directed to non-statutory subject matter.
Claim 15 recites a computer accessible medium. Under the broadest reasonable interpretation consistent with the specification, computer accessible media include transitory propagating signals per se. As a result, claim 15 is directed to signals. However, signals are not a statutory class of invention. Accordingly, claim 15 is rejected because it is not directed to statutory subject matter.
Claims 16-19 and 21 fail to introduce sufficient limitations to remedy the deficiencies of claim 15 and are similarly rejected for being directed to non-statutory subject matter.
Claim Rejections - 35 U.S.C. § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. § 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 1-5, 8-12, 15-19, 22, and 25 are rejected under 35 U.S.C. § 102(a)(1)-(2) as being anticipated by Shapiro (WO 2022/072346 A1).
Claims 1, 8, and 15: Shapiro, as shown, discloses the following limitations:
converting, by at least one computer processor, clinical notes to training data using at least one natural language processing procedure (see at least ¶ [0024]: in some embodiments, (b) further comprises parsing the structured information or textual information of the first information using one or more algorithms selected from the group consisting of a text recognition algorithm, a regular expressions algorithm, a pattern recognition algorithm, an imaging recognition algorithm, a natural language processing algorithm, an optical character recognition algorithm, a term frequency-inverse document frequency (TF-IDF) algorithm, and a bag-of-words algorithm. In some embodiments, (d) further comprises parsing the structured information or textual information of the second information using one or more algorithms selected from the group consisting of a text recognition algorithm, a regular expressions algorithm, a pattern recognition algorithm, an imaging recognition algorithm, a natural language processing algorithm, an optical character recognition algorithm, a term frequency-inverse document frequency (TF-IDF) algorithm, and a bag-of-words algorithm; see also at least ¶¶ [0025]: in some embodiments, (b) further comprises determining, based at least in part on the parsing in (b), whether the structured information or textual information of the first information corresponds to a clinical trials database, a clinical trial arm description, a genomics database, a clinical care guideline document, a case series document, a drug database, an imaging report, a pathology report, a clinic note, a progress note, a genomics report, a laboratory test report, a diagnostic report, or a prognostic report. In some embodiments, (d) further comprises determining, based at least in part on the parsing in (d), whether the structured information or textual information of the second information corresponds to an imaging report, a pathology report, a clinic note, a progress note, a genomics report, a laboratory test report, a diagnostic report, or a prognostic report; see also at least ¶ [0127]);
training, by the at least one computer processor, a machine learning model using the training data (see at least ¶ [0034]: in some embodiments, (e) further comprises combining outputs from a plurality of mappings, and generating the ranked set of candidate treatments based at least in part on the combined outputs. In some embodiments, combining the outputs comprises summing the outputs from the plurality of mappings. In some embodiments, combining the outputs comprises using a set of weights to calculate a weighted sum of the outputs from the plurality of mappings. In some embodiments, combining the outputs comprises normalizing or scaling the set of weights. In some embodiments, the set of weights comprises values between 0 and 1. In some embodiments, the set of weights is adjusted using a training set. In some embodiments, the set of weights is adjusted by XGBoost, Bayesian rejection sampling, Thompson Sampling, upper confidence bound sampling, or knowledge gradient sampling. In some embodiments, the set of weights is adjusted based on a distance metric between a model-predicted treatment ranking and an observed treatment ranking. In some embodiments, the distance metric comprises a Kendall tau distance; see also at least ¶¶ [0088] and [0124]);
finetuning, by the at least one computer processor, the trained machine learning model based on selected parameters (see at least ¶ [0034] and the analysis above; see also at least ¶¶ [0036], [0088], [0124], and [0158]);
receiving patient data (see at least ¶ [0036]: in some embodiments, the method further comprises performing at least one iteration of (a) and (b) to incorporate new or updated medical information into the first document corpus. In some embodiments, (b) comprises using a Bayesian update process to incorporate the new or updated medical information into the first document corpus. In some embodiments, (b) comprises, subsequent to the subject being followed to a specified endpoint, incorporating the new or updated medical information of the subject into the first document corpus, thereby allowing additional subjects to benefit therefrom. In some embodiments, the method further comprises performing (c) to (e) for an additional subject in need of an individual recommendation for medical treatment; see also at least ¶¶ [0120] and [0133]-[0135]); and
generating, by the at least one computer processor, the at least one medical prediction on the received patient data with the trained finetuned machine learning model (see at least ¶ [0037]: a system for generating an individual recommendation for medical treatment of a subject, comprising: a database that is configured to (i) receive from a first set of distinct sources, first information relating to a set of diseases or disorders encompassing a medical domain, and (ii) receive from a second set of distinct sources, second information relating to a disease or disorder of the subject, wherein the second information comprises a clinical information of the subject; and one or more computer processors operatively coupled to the database, wherein the one or more computer processors are individually or collectively programmed to: (a) process the first information relating to the set of diseases or disorders to generate a first document corpus, wherein processing the first information comprises parsing structured information or textual information of the first information; (b) process the second information relating to the disease or disorder of the subject to generate a second document corpus, wherein processing the second information comprises parsing structured information or textual information of the second information; and (c) generate a ranked set of candidate treatments for treating the disease or disorder of the subject, based at least in part on processing the first document corpus with the second document corpus; see also at least ¶¶ [0034], [0157]-[0159], and [0161]).
Claims 2, 9, and 16: Shapiro discloses the limitations as shown in the rejections above. Further, Shapiro, as shown, discloses the following limitations:
wherein the clinical notes include at least one of (i) structured data and unstructured data, or (ii) discharge notes (see at least ¶ [0041]: in some embodiments, the case summary is prepared by a health care provider of the subject. In some embodiments, the health care provider comprises a physician. In some embodiments, the physician comprises an oncologist. In some embodiments, the case summary comprises structured data, unstructured data, or a combination thereof. In some embodiments, the case summary is conveyed from an electronic health record system. In some embodiments, the case summary comprises at least one of genomic features of the subject, treatment options for the subject, and tumor load of the subject).
Claims 3, 10, and 17: Shapiro discloses the limitations as shown in the rejections above. Further, Shapiro, as shown, discloses the following limitations:
integrating the trained finetuned machine learning model in real-time with clinical workflows (see at least ¶ [0056]: in some embodiments, (c) further comprises combining outputs from a plurality of mappings, and generating the ranked set of candidate treatments based at least in part on the combined outputs. In some embodiments, combining the outputs comprises summing the outputs from the plurality of mappings. In some embodiments, combining the outputs comprises using a set of weights to calculate a weighted sum of the outputs from the plurality of mappings. In some embodiments, combining the outputs comprises normalizing or scaling the set of weights. In some embodiments, the set of weights comprises values between 0 and 1. In some embodiments, the set of weights is adjusted using a training set. In some embodiments, the set of weights is adjusted by XGBoost, Bayesian rejection sampling, Thompson Sampling, upper confidence bound sampling, or knowledge gradient sampling. In some embodiments, the set of weights is adjusted based on a distance metric between a model-predicted treatment ranking and an observed treatment ranking. In some embodiments, the distance metric comprises a Kendall tau distance; see also at least ¶¶ [0007]-[0011]).
Claims 4, 11, and 18: Shapiro discloses the limitations as shown in the rejections above. Further, Shapiro, as shown, discloses the following limitations:
wherein the machine learning model is trained using non-clinical data (see at least ¶ [0121]: in operation 412, inclusion and/or exclusion criteria, such as patient performance status, prior failed treatments, minimum and maximum allowed lab values indicating adequate organ function, etc., may be extracted and standardized. In operation 413, some or all of the prior data may be labeled (e.g., disease, drugs, inclusion and/or exclusion) in the text).
Claims 5, 12, and 19: Shapiro discloses the limitations as shown in the rejections above. Further, Shapiro, as shown, discloses the following limitations:
wherein the at least one medical prediction includes information associated with a readmission to a hospital (see at least ¶ [0121]: in operation 412, inclusion and/or exclusion criteria, such as patient performance status, prior failed treatments, minimum and maximum allowed lab values indicating adequate organ function, etc., may be extracted and standardized. In operation 413, some or all of the prior data may be labeled (e.g., disease, drugs, inclusion and/or exclusion) in the text; see also at least ¶¶ [0034], [0037], [0157]-[0159], and [0161]).
Claims 22 and 25: Shapiro, as shown, discloses the following limitations:
a computer processor implementing an artificial intelligence model configured to generate code to create a structured database procedure (see at least ¶ [0111]: generating these options may comprise a number of operations. First, sources of reliable, trusted knowledge may be ingested to provide a document corpus that may serve as reference material. Then, this reference material may be organized according to the questions that may be asked. That is, the ontology of the questions (patient features, disease state, types of treatments, etc.) may be properly scoped; see also at least ¶ [0112]: there may be two phases to this process: a training phase, and the execution phase. The training phase may comprise the analysis of large amounts of data from a variety of sources to perform a variety of tasks, such as: Discover concepts in documents pertaining to clinical trials, tumor board discussions regarding specific patients, and other such source materials; Generate a topic space for a corpus of documents; and, Associate one or more topics with specific documents).
Claims 31-33, 35, 37, and 38 are rejected under 35 U.S.C. § 102(a)(1)-(2) as being anticipated by Wei et al. (U.S. Pub. No. 2020/0265273 A1) (hereinafter “Wei”).
Claims 31 and 38: Wei, as shown, discloses the following limitations:
a computer processor configured to train the EHR artificial intelligence model on a training data set that comprises a plurality of EHR records utilizing an under-sampling technique (see at least ¶ [0115]: the system 100 implements a deep learning approach to identify or detect adverse events (such as bleeding and/or thermal injury) from a recording (e.g., video data), and can simultaneously estimate the severity of the adverse event. The approach can include specific technical improvements which were identified during testing to aid with technical issues that arose during practical implementation; see also at least ¶ [0116]: the system 100 can use pre-trained models and re-train the models with data from self-recorded videos to maximize the effectiveness of the deep learning algorithms to perform their bleeding detection and classification/estimation task. Furthermore, these models can be used in combination with an attention mechanism to visualize high-level adverse event features as a reasoning layer of bleeding and/or thermal injury detection and estimation; see also at least ¶¶ [0036], [0149], [0162], and [0289]).
Claim 32: Wei discloses the limitations as shown in the rejections above. Further, Wei, as shown, discloses the following limitations:
wherein the under-sampling technique comprises at least one of (i) an iterative summation, (ii) a hierarchy, or (iii) a sparse-attention model (see at least ¶ [0205]: for production, the process 300 deploys the selected model onto the server. The process 300 converts the selected model into a graph. An application can convert the model to a graph data format. This can allow process 300 to deploy the model into the server for production in a smaller size. It can contain multiple graphs (resulting from different training) into one file and do inference on different tasks with just one file. Models can be very large in the training process. In production, training parameters might not be needed anymore. The process 300 extracts data from the database 302 and feeds the data into the selected model to compute the severity estimation. The model can be deployed in a way that online training is allowed. As noted, the process 300 compares the previous models and selects the best model. The process 300 deploys the selected model onto the server. The model is updated using online learning and training. The sampled data can be used for online training. The weight can be updated in models on the server. The weight update can be like another new training however based on previous trained weights. The model can contain weights from offline training, and the online training can update the weights by training on new data. Once this is done, the model will be fed into the comparison algorithm to select the best model. If this model is identified to be better than the others, than this one will be deployed to the server to replace the former one. The process 300 can compare to previous model performance and decide whether to update or not. This can be fed back to the model selection algorithm, which can select a model based on accuracy, loss, and F1 scores. The selection can be based on either a new loss function or a confidence score that implements a weighted average on those metrics, for example).
Claim 33: Wei discloses the limitations as shown in the rejections above. Further, Wei, as shown, discloses the following limitations:
wherein the iterative summation comprises a procedure which:
selects, by the computer processor, a fixed amount of data from a selected one of the plurality of EHR records (see at least ¶ [0205]: for production, the process 300 deploys the selected model onto the server. The process 300 converts the selected model into a graph. An application can convert the model to a graph data format. This can allow process 300 to deploy the model into the server for production in a smaller size. It can contain multiple graphs (resulting from different training) into one file and do inference on different tasks with just one file. Models can be very large in the training process. In production, training parameters might not be needed anymore. The process 300 extracts data from the database 302 and feeds the data into the selected model to compute the severity estimation. The model can be deployed in a way that online training is allowed. As noted, the process 300 compares the previous models and selects the best model. The process 300 deploys the selected model onto the server. The model is updated using online learning and training. The sampled data can be used for online training. The weight can be updated in models on the server. The weight update can be like another new training however based on previous trained weights. The model can contain weights from offline training, and the online training can update the weights by training on new data. Once this is done, the model will be fed into the comparison algorithm to select the best model. If this model is identified to be better than the others, than this one will be deployed to the server to replace the former one. The process 300 can compare to previous model performance and decide whether to update or not. This can be fed back to the model selection algorithm, which can select a model based on accuracy, loss, and F1 scores. The selection can be based on either a new loss function or a confidence score that implements a weighted average on those metrics, for example; see also at least ¶¶ [0169] and [0218]);
summarizes, by the computer processor, information in the fixed amount of data (see at least ¶ [0205] and the analysis above; see also at least ¶¶ [0169] and [0218]);
selects, by the computer processor, a next fixed amount of data from the selected EHR record (see at least ¶ [0205] and the analysis above; see also at least ¶¶ [0169] and [0218]);
feeds, by the processor, the summary and the next fixed amount of data back into the EHR artificial intelligence model (see at least ¶ [0205] and the analysis above; see also at least ¶¶ [0169] and [0218]); and
creates, by the processor, an updated summary based on the summary and next fixed amount of data (see at least ¶ [0205] and the analysis above; see also at least ¶¶ [0029], [0169], and [0218]).
Claim 35: Wei discloses the limitations as shown in the rejections above. Further, Wei, as shown, discloses the following limitations:
wherein the hierarchy comprises a procedure which:
selects, by the computer processor, a first fixed amount of data from a selected one of the plurality of EHR records (see at least ¶ [0205]: for production, the process 300 deploys the selected model onto the server. The process 300 converts the selected model into a graph. An application can convert the model to a graph data format. This can allow process 300 to deploy the model into the server for production in a smaller size. It can contain multiple graphs (resulting from different training) into one file and do inference on different tasks with just one file. Models can be very large in the training process. In production, training parameters might not be needed anymore. The process 300 extracts data from the database 302 and feeds the data into the selected model to compute the severity estimation. The model can be deployed in a way that online training is allowed. As noted, the process 300 compares the previous models and selects the best model. The process 300 deploys the selected model onto the server. The model is updated using online learning and training. The sampled data can be used for online training. The weight can be updated in models on the server. The weight update can be like another new training however based on previous trained weights. The model can contain weights from offline training, and the online training can update the weights by training on new data. Once this is done, the model will be fed into the comparison algorithm to select the best model. If this model is identified to be better than the others, than this one will be deployed to the server to replace the former one. The process 300 can compare to previous model performance and decide whether to update or not. This can be fed back to the model selection algorithm, which can select a model based on accuracy, loss, and F1 scores. The selection can be based on either a new loss function or a confidence score that implements a weighted average on those metrics, for example; see also at least ¶¶ [0112], [0169], [0217]-[0218], and [0346]);
converts, by the computer processor, the first fixed amount of data into a machine language (see at least ¶ [0205] and the analysis above; see also at least ¶¶ [0112], [0169], [0217]-[0218], and [0346]);
selects, by the computer processor, a second fixed amount of data from the selected EHR record (see at least ¶ [0205] and the analysis above; see also at least ¶¶ [0112], [0169], [0217]-[0218], and [0346]); and
converts, by the computer processor, the second fixed amount of data into a machine language that is added to the machine language for the first fixed amount of data (see at least ¶ [0205] and the analysis above; see also at least ¶¶ [0112], [0169], [0217]-[0218], and [0346]).
Claim 37: Wei discloses the limitations as shown in the rejections above. Further, Wei, as shown, discloses the following limitations:
wherein the sparse-attention model comprises a procedure which:
selects, by the computer processor, a word sampling rate for the plurality of EHR records (see at least ¶ [0205]: for production, the process 300 deploys the selected model onto the server. The process 300 converts the selected model into a graph. An application can convert the model to a graph data format. This can allow process 300 to deploy the model into the server for production in a smaller size. It can contain multiple graphs (resulting from different training) into one file and do inference on different tasks with just one file. Models can be very large in the training process. In production, training parameters might not be needed anymore. The process 300 extracts data from the database 302 and feeds the data into the selected model to compute the severity estimation. The model can be deployed in a way that online training is allowed. As noted, the process 300 compares the previous models and selects the best model. The process 300 deploys the selected model onto the server. The model is updated using online learning and training. The sampled data can be used for online training. The weight can be updated in models on the server. The weight update can be like another new training however based on previous trained weights. The model can contain weights from offline training, and the online training can update the weights by training on new data. Once this is done, the model will be fed into the comparison algorithm to select the best model. If this model is identified to be better than the others, than this one will be deployed to the server to replace the former one. The process 300 can compare to previous model performance and decide whether to update or not. This can be fed back to the model selection algorithm, which can select a model based on accuracy, loss, and F1 scores. The selection can be based on either a new loss function or a confidence score that implements a weighted average on those metrics, for example; see also at least ¶¶ [0112], [0169], [0217]-[0218], and [0346]);
applies, by the computer processor, the word sampling rate to the plurality of EHR records (see at least ¶ [0205] and the analysis above; see also at least ¶¶ [0112], [0169], [0217]-[0218], and [0346]); and
trains, by the computer processor, the EHR artificial intelligence model on the plurality of EHR records subject to the word sampling rate (see at least ¶ [0205] and the analysis above; see also at least ¶¶ [0112], [0169], [0217]-[0218], and [0346]).
Claim Rejections - 35 U.S.C. § 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.
Claims 7, 14, and 21 are rejected under AIA 35 U.S.C. § 103 as being unpatentable over Shapiro (WO 2022/072346 A1) in view of Wang et al. (CN-116204607-A) (hereinafter “Wang”).
Claims 7, 14, and 21: Shapiro discloses the limitations as shown in the rejections above.
Shapiro does not explicitly disclose, but Wang, as shown, teaches the following limitations:
wherein the trained machine learning model is finetuned by replacing the trained machine learning model with a randomly initialized linear classifier after a last hidden layer of a pretrained BERT model (see at least p. 27: Because the data set is much smaller on the sentence number and the average sentence length, and there is no representation of the dictionary attention to enhance the needed entity coding, must first through one entity discovery related task fine tuning, to realize the learning of the model entity discovery task. As shown in FIG. 3, the embodiment method designs a two-stage fine tuning way to finish the training task. The first step, data preparation: pre-downloading Chinese BERT pre-training model, Chinese entity discovery and linking task public data set, finishing the knowledge point label data set for training course entity label. the second step: Generic entity discovery and link fine tuning: The method of the embodiment uses the universal entity discovery and link task to perform the first fine adjustment. universal entity link sample such as shown in FIG. 4, in the universal field web page text for all entities in Baidu range in the identification and link of the task, the course entity marking task is close to the text. The specific fine tuning process is shown in the ELQ document (Li, Belinda Z, Sewon Min, Srinivasan Iyer, Yashar Mehdad, and Wen-tau Yih.202020. End-to-End Entity Linking for Questions, " In Proc. Of EMNLP, 6433-41.), the training method in this stage is not in the scope of the present invention. The fine tuning update context encoder, entity encoder, parameter of linear classifier. the third step, course entity marking training: keeping the context encoder, entity encoder, parameter of linear classifier, randomly initializing parameter of the layer, inputting the knowledge point label data set for fine tuning. using reverse propagation algorithm to update the network parameter in each layer in the entity labelling model DsMOOC, after finishing training, obtaining the entity labelling model DsMOOC).
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to combine the fine-tuning techniques taught by Wang with the medical diagnostics systems disclosed by Shapiro, because Wang teaches at page 26 that its techniques “represents the benefits of two aspects: In one aspect, it is composed of the title and information of the entity, using the same BERT model coding calculation to be represented in the same space with the word. on the other hand, compared with the directly using entity in the sentence context represents calculating the average value, BE (ei-n) keeps the independence, also fully uses the information of one side of the knowledge base.” See M.P.E.P. § 2143(I)(G).
Claims 23 and 24 are rejected under AIA 35 U.S.C. § 103 as being unpatentable over Shapiro (WO 2022/072346 A1) in view of Ghauri et al. (U.S. Pub. No. 2022/0375556 A1) (hereinafter “Ghauri”).
Claim 23: Shapiro discloses the limitations as shown in the rejections above. Further, Shapiro, as shown, discloses the following limitations:
wherein the code is generated by the artificial intelligence model to create the structured database procedure (see at least ¶ [0111]: generating these options may comprise a number of operations. First, sources of reliable, trusted knowledge may be ingested to provide a document corpus that may serve as reference material. Then, this reference material may be organized according to the questions that may be asked. That is, the ontology of the questions (patient features, disease state, types of treatments, etc.) may be properly scoped; see also at least ¶ [0112]: there may be two phases to this process: a training phase, and the execution phase. The training phase may comprise the analysis of large amounts of data from a variety of sources to perform a variety of tasks, such as: Discover concepts in documents pertaining to clinical trials, tumor board discussions regarding specific patients, and other such source materials; Generate a topic space for a corpus of documents; and, Associate one or more topics with specific documents).
Shapiro does not explicitly disclose, but Ghauri, as shown, teaches the following limitations:
wherein the code cases the computer processor to convert unstructured text into a plurality of SQL tables (see at least ¶ [0021]: FIG. 1 further shows that server 102 includes a database or repository 104, which may be a relational database comprising a Structured Query Language (SQL) database stored in a SQL server. Device 131 may also include its own database. The repository 104 serves data from a database, which is a repository for data used by server 102 and device 131 during the course of operation of the disclosed embodiments. Database 104 may be distributed over one or more nodes or locations that are connected via network 106).
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to combine the data management techniques taught by Ghauri with the medical diagnostics systems disclosed by Shapiro, because Ghauri teaches at ¶ [0018] that its techniques “reduce or eliminate the need for the medical professionals to dedicating more work hours to converting physician notes into proper medical billing codes for medical billing.” See M.P.E.P. § 2143(I)(G).
Moreover, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to combine the data management techniques taught by Ghauri with the medical diagnostics systems disclosed by Shapiro, because the claimed invention is merely a combination of old elements (the data management techniques taught by Ghauri and the medical diagnostics systems disclosed by Shapiro), in the combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable. See M.P.E.P. § 2143(I)(A).
Claim 24: The combination of Shapiro and Ghauri teaches the limitations as shown in the rejections above. Further, Shapiro, as shown, discloses the following limitations:
wherein the unstructured text comprises electronic health records free text (see at least ¶ [0041]: in some embodiments, the case summary is prepared by a health care provider of the subject. In some embodiments, the health care provider comprises a physician. In some embodiments, the physician comprises an oncologist. In some embodiments, the case summary comprises structured data, unstructured data, or a combination thereof. In some embodiments, the case summary is conveyed from an electronic health record system. In some embodiments, the case summary comprises at least one of genomic features of the subject, treatment options for the subject, and tumor load of the subject).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant’s disclosure. The following references have been cited to further show the state of the art with respect to digitizing clinical impressions and data.
Sheffer et al. (U.S. Pub. No. 2020/0126667 A1) (automated clinical indicator recognition with natural language processing);;
Liu et al. (“A new data visualization and digitization method for building electronic health record.” 2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). IEEE, 2020).
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Christopher Tokarczyk, whose telephone number is 571-272-9594. The examiner can normally be reached Monday-Thursday between 6:00 AM and 4:00 PM Eastern.
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, Mamon Obeid, can be reached at 571-270-1813. 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.
/CHRISTOPHER B TOKARCZYK/ Primary Examiner, Art Unit 3687
Prosecution Insights