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 Claims
In the response dated April 8th, 2026, Applicant amended claims 1 and 6. Applicant added claims 21-30. Claims 11-20 are canceled. Claims 1-10 and 21-30 are pending.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on January 24, 2025 is being considered by the examiner.
Response to Arguments
In response to the argument put forward in the amendment, Examiner will address them in the order they were presented.
Regarding pages 8-11, Applicant’s arguments have been considered but are moot in view of the amended claim language.
Regarding page 12-13, Applicant’s arguments have been considered but are unpersuasive. Applicant argues that the claims solve the conventional issue of reconciling different characteristics of pathomic, radiomic, and transcriptomic data that occurs from separate training of machine learning models. The Examiner respectfully disagrees. MPEP 2106.04(d)(1) and MPEP 2106.05(a) indicates that a practical application may be present where the claimed invention provides a technical solution to a technical problem. See, e.g., DDR Holdings, LLC. v. Hotels.com, L.P., 773 F.3d 1245, 1259 (Fed. Cir. 2014) (finding that claiming a website that retained the “look and feel” of a host webpage provided a technological solution to the problem of retention of website visitors by utilizing a website descriptor that emulated the “look and feel” of the host webpage, where the problem arose out of the internet and was thus a technical problem). Here, while Applicant’s argued problem is a technical problem, there is no nexus between the argued problem and the argued solution because there is no indication that the claimed invention actually solves this problem. The Applicant has identified that there is a technical problem relating to communication of information between transmitting syndicated information across language models; however, there is no indication that the claim actually solves this problem. The claim does not define what cross-scale correlation between various data types must or must not contain and thus the claim may actually weaken existing correlation between different diagnostic characteristics of data types. Because the claim does not explicitly solve this technical problem, a practical application is not present.
Regarding page 13-16, Applicant’s arguments have been considered but are moot in view of the amended claim language.
Regarding page 17-20, Applicant’s arguments have been considered but are moot in view of the amended claim language.
Regarding page 21, Applicant’s arguments have been considered but are unpersuasive. Applicant argues that the combination of combination proposal is driven by hindsight and would not have been routine or predictable for a person of ordinary skill. MPEP 2145 states that “’[a]ny judgment on obviousness is in a sense necessarily a reconstruction based on hindsight reasoning, but so long as it takes into account only knowledge which was within the level of ordinary skill in the art at the time the claimed invention was made and does not include knowledge gleaned only from applicant’s disclosure, such a reconstruction is proper.’” and that “there is no requirement that an ‘express, written motivation to combine must appear in prior art references before a finding of obviousness.’”. Examiner believes that a person having ordinary skill in the art would have reason to combine the cited prior art with a reasonable expectation of success. Therefore, Examiner maintains the rejection under 35 U.S.C. 103.
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 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception without significantly more.
Step 1
The claims recite subject matter within a statutory category as a process, machine, and/or article of manufacture. However, it will be shown in the following steps, that claims 1-20 are nonetheless unpatentable under 35 U.S.C. 101.
Step 2A Prong One
Claim 26 states:
A computer program product stored on a non-transitory computer-readable medium and comprising machine-executable instructions, wherein, in response to being executed, the machine-executable instructions cause a system to perform operations, comprising:
receiving pathomic information comprising pathomic imaging data associated with a set of patients, radiomic information comprising radiomic imaging data associated with the set of patients, and transcriptomic information comprising transcriptomic data associated with the set of patients;
generating a multimodal model, wherein generating the multimodal model comprises: combining the pathomic information, radiomic information, and transcriptomic information into a training dataset, and training, using the training dataset, the multimodal model to: generate a graph using the pathomic information, radiomic information, and transcriptomic information, and recommend treatments for medical conditions of patients based on the graph;
applying patient data to the multimodal model, wherein the patient data pertains to a medical condition of a patient;
generating, based on application of the patient data to the multimodal model, a recommended treatment, wherein the recommended treatment is based on at least one node of the graph-having sufficient similarity to the patient data;
determining a risk score for the recommended treatment, wherein the risk score presents a measure of a successful treatment outcome for the recommended treatment regarding the patient's medical condition, wherein the risk score is determined based on applying the recommended treatment to a probability model;
and presenting the recommended treatment and risk score for review.
The broadest reasonable interpretation of these steps includes “organizing human activity” and/or “mental processes” because each bolded component can practically be performed by the human mind or with pen and paper. Other than reciting generic computer terms like “computer product”, “non-transitory computer-readable medium”, or “multimodal model”, nothing in the claims precludes the bold-font portions from practically being performed in the mind. For example, “determining a risk score for the recommended treatment, wherein the risk score presents a measure of a successful treatment outcome for the recommended treatment regarding the patient's medical condition, wherein the risk score is determined based on applying the recommended treatment to a probability model” in the context of this claim encompasses a mental process of a healthcare professional analyzing the results form a computer to determine the risk profile of a patient’s disease progression. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” or “Organizing Human Activity” grouping of abstract ideas. Accordingly, the claim recites an abstract idea.
generating, based on application of the patient data to the multimodal model, a recommended treatment, wherein the recommended treatment is based on at least one node of the graph-having sufficient similarity to the patient data;
determining a risk score for the recommended treatment, wherein the risk score presents a measure of a successful treatment outcome for the recommended treatment regarding the patient's medical condition, wherein the risk score is determined based on applying the recommended treatment to a probability model;
and presenting the recommended treatment and risk score for review
as drafted, could lay out the management of human behavior by a physician performing a differential diagnosis on a patient. Under the broadest reasonable interpretation, these steps include multiple abstract ideas that will be identified as a single abstract idea moving forward.
Independent claims 1 and 17 cover similar steps of generating a multimodal model, determining a potential patient treatment protocol, determine a probability of this protocol being successful, and presenting a recommendation. These claims fall under the same category of an abstract idea and follows the same rationale as claim 26.
Dependent claims recite additional subject matter which further narrows or defines the abstract idea embodied in the claims (such as claim 3, reciting particular aspects of how “receiving a confirmation to implement the recommended treatment; and updating the patient data in accordance with the recommended treatment being applied to treat the patient's medical condition” may be performed in by a human but for recitation of generic computer components).
Dependent claims 3, 4, 23, 28, and 30 add additional elements to their parent claims which will be further inspected in the following steps for a practical application to their abstract idea.
Step 2A Prong Two
This judicial exception of “Mental Processes” or “Organizing Human Activity” is not integrated into a practical application. Independent claim 26’s product recites additional elements such as “computer product”, “non-transitory computer-readable medium”, or “multimodal model”. In addition to the generic components and additional elements listed above, independent claims 1 and 21 ’s system and method also includes a “memory”, “processor”, and “non-transitory computer readable medium”. The multimodal model, nodes and graph will be analyzed further for conventionality in the following steps. The other additional elements will be treated as generic computer components. In particular, these additional elements do not integrate the abstract idea into a practical application because the additional elements:
amount to mere instructions to apply an exception (such as recitation of “A computer-implemented method comprising: generating, by a device comprising at least one processor, a multimodal model, wherein the multimodal model is generated based on at least one of a medical condition of a patient, historical data pertaining to the medical condition, imaging data pertaining to the medical condition, or medical knowledge pertaining to the medical condition”, “wherein the treatment is an output of the multimodal model” and “wherein the probability is determined based on application of the potential treatment to a probability model” amounts to invoking computers as a tool to perform the abstract idea, see applicant’s specification [0164], see MPEP 2106.05(f))
add insignificant extra-solution activity to the abstract idea (such as recitation of “the probability model comprises a collection of treatments in conjunction with success of application of a respective treatment in the collection of treatments to a respective medical condition, wherein the probability is assigned to a risk score for the potential treatment of the patient’s medical condition” 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. For instance, dependent claim 4 reference additional elements of an interactive display alongside a mouse and cursor to their parent claims. Additionally, claim 8 “wherein the recommended treatment is a first recommended treatment and the risk score is a first risk score, wherein the operations further comprise: generating, based on application of the patient data to the multimodal model, a second recommended treatment, wherein the second recommended treatment is based on at least one node in the sequence of nodes having sufficient similarity to the patient data;” and claim 8 “and presenting the ranking of the first recommended treatment and first risk score, and the second recommended treatment and the second risk score”, amounts to necessary data outputting, see MPEP 2106.05(g)), recitation of claim 3 “utilizing natural language programming to facilitate interaction with the presented recommended treatment and risk score” and claim 4 “wherein the interaction is via at least one of a mouse and cursor, interactive display, or speech-based interaction” and claim 8 “determining a second risk score for the second recommended treatment, wherein the second risk score presents a measure of a successful treatment outcome for the second recommended treatment regarding the patient’s medical condition, wherein the second risk score is determined based on applying the second recommended treatment to a probability model;” and claim 8 “ranking the first recommended treatment and the second recommended treatment based on the first risk score and the second risk score;” amounts to insignificant application). 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 remaining dependent claims 5-7, 9-10 and 21, 22, 24-27 and 29-30 do not recite additional elements or activity but further narrow or define the abstract idea embodied in the claims and hence also do not integrate the aforementioned abstract idea into a practical application.
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 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, amount to no more than limitations which amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields.
As previously noted, the claim recites an additional element of multimodal models. Tetsuro et al. (JP2000250677) demonstrates “the processing of the conventional multimodal interface will be described below” that multimodal modeling was conventional before the priority data of the claimed invention. As such, this additional element, individually and in combination with the prior additional element, does not amount to significantly more.
To elaborate:
“receiving pathomic information comprising pathomic imaging data associated with a set of patients, radiomic information comprising radiomic imaging data associated with the set of patients, and transcriptomic information comprising transcriptomic data associated with the set of patients” is equivalently, receiving or transmitting data over a network, Symantec, MPEP 2106.05(d)(II)(i);
“generating a multimodal model, wherein generating the multimodal model comprises: combining the pathomic information, radiomic information, and transcriptomic information into a training dataset,” is equivalently, electronic recordkeeping, Alice Corp., MPEP 2106.05(d)(II)(iii);
“and training, using the training dataset, the multimodal model to: generate a graph using the pathomic information, radiomic information, and transcriptomic information, and recommend treatments for medical conditions of patients based on the graph” is equivalently, Determining an estimated outcome, OIP Techs., MPEP 2106.05(d)(II)(v)
“applying patient data to the multimodal model, wherein the patient data pertains to a medical condition of a patient”, is equivalently, electronic recordkeeping, Alice Corp., MPEP 2106.05(d)(II)(iii);
Dependent claims recite additional subject matter which, as discussed above with respect to integration of the abstract idea into a practical application, 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. Dependent claims recite additional subject matter which amount to limitations consistent with the additional elements in the independent claims. These additional limitations amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields.
As previously noted, claim 4 recites an additional element of a mouse and cursor. Mei et al. (US20020118167) demonstrates in paragraph [0007] “Conventional mice for cursor moving/placing, object picking, editing, drawing, painting, menu selecting, window opening and closing, etc. are not used in notebook computer systems” that a mouse and cursor were conventional long before the priority data of the claimed invention. As such, this additional element, individually and in combination with the prior additional element, does not amount to significantly more.
As previously noted, the claims recite an additional element of a graph and nodes. Minato (Pat. 5493504) demonstrates “a graph including smaller number of nodes than a conventional graph” was conventional before the priority data of the claimed invention. As such, this additional element, individually and in combination with the prior additional element, does not amount to significantly more.
To elaborate:
claim 3 and 2 “utilizing natural language programming to facilitate interaction with the presented recommended treatment and risk score”, is equivalently, a web browser’s back and forward button functionality, Internet Patent Corp., MPEP 2106.05(d)(II)(vi))
claim 4 “wherein the interaction is via at least one of a mouse and cursor, interactive display, or speech-based interaction” , is equivalently, a web browser’s back and forward button functionality, Internet Patent Corp., MPEP 2106.05(d)(II)(vi))
is equivalently, Arranging a hierarchy of groups, sorting information, Versata Dev. Group, Inc. v. SAP Am., Inc., 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.
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 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 1-3, 5-12, and 21-30 are rejected under 35 U.S.C. 103 as being unpatentable over Bui et al. (20240339217) in view Thierry et al. (EP4307315).
Regarding claim 1, Bui teaches.
A system, comprising: at least one processor; and ([0131] The user computing system 102 includes one or more processors 112 and a memory 114”)
a memory that stores executable instructions that, when executed by the at least one processor, facilitate performance of operations, comprising: ([0131] “memory”)
receiving pathomic information comprising pathomic imaging data associated with a set of patients, ([0048] “the systems and methods disclosed herein can allow a computing system to receive a plurality of images of a patient's skin.” comprises receiving pathomic information)
generating a multimodal model, wherein generating the multimodal model comprises combining the pathomic information, radiomic information, and transcriptomic information into a training dataset, ([0089] “The medical conditions classification model may be trained and/or configured for multimodal processing. In some implementations, the medical conditions classification model can process a multimodal query and/or context data to generate the one or more predicted condition classifications… The one or more candidate medical conditions can include skin conditions, hair conditions, infections, cardiovascular conditions, dental conditions, oral conditions, podiatry conditions, genetic conditions, rheumatology conditions, diabetes side effects, blood conditions, cancer classifications, gastrointestinal conditions, trauma conditions, benign cosmetic conditions, eye conditions, and/or other medical condition” comprises receiving information to generate a multimodal model)
and training, using the training dataset, the multimodal model to ([0156] “A set of training data can include a plurality of training instances divided between multiple datasets” and [0159] “Training and/or tuning can include updating the machine-learned model using the evaluation signal.”)
generate a graph using the pathomic information, radiomic information, and transcriptomic information, and recommend treatments for medical conditions of patients based on the graph ([0196] “The one or more generative models 90 can include … graph generation models… to generate predicted data” see also [0090] “computing system can then provide the annotated image for display with the medical condition information as an output. The annotated image may include annotations generated based on the medical condition information (e.g., label overlays, treatment”)
applying patient data to the multimodal model, wherein the patient data pertains to a medical condition of a patient; ([0048] “metadata associated with the patient can also be additionally input into the model… the additional patient metadata can include patient demographic information, medical history, and/or other information concerning the patient (e.g., the user).”)
generating, based on application of the patient data to the multimodal model, a recommended treatment, ([0048] “the machine-learned skin condition classification model can be configured to jointly process such additional patient metadata alongside the input imagery to produce the output skin condition classification”) wherein the recommended treatment is based on at least one node of the graph, having sufficient similarity to the patient data; ([0211] “In general, prediction layers can leverage various kinds of artificial neural networks that can understand or generate sequences of information” and [0196] “The one or more generative models 90 can include … graph generation models… to generate predicted data” see also [0090] “computing system can then provide the annotated image for display with the medical condition information as an output. The annotated image may include annotations generated based on the medical condition information (e.g., label overlays, treatment”)
Regarding claim 1, Bui does not explicitly teach, as taught by Thierry:
receiving… radiomic information comprising radiomic imaging data associated with the set of patients, ([0076] “Radiological data, also referred to as radiomics data, are images collected and include, but are not limited to, computerized tomography (CT)” and [0078] “These images may be acquired from the patient examination”) and transcriptomic information comprising transcriptomic data associated with the set of patients ([0062] “Biological data for the patient may include digital pathology data and proteomic data.” And [0063] The term "genomic data" refers to a digital representation of genomic information, such as a DNA sequence”)
determining a risk score for the recommended treatment, wherein the risk score presents a measure of a successful treatment outcome for the recommended treatment regarding the patient’s medical condition, wherein the risk score is determined based on applying the recommended treatment to a probability model; and ([0015] “a trained prediction machine learning model trained to predict patient's treatment response or treatment efficacy” where the treatment efficacy comprises presenting a measure of a successful treatment outcome for the recommended treatment in the form of a risk score)
presenting the recommended treatment and risk score for review. ([0015] “and output prediction of the patient's response to the treatment or prediction of the patient's treatment efficacy defined as length of time to an event.”)
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Bui with the teachings of Thierry, with a reasonable expectation of success, by explicitly using a probabilistic model to calculate a risk score using biological, genomic and radiological information. This would have improved the accuracy of developing a patient’s successful treatment protocol and thus reduce risks on diagnostic protocols. Thierry is adaptable to Bui as both inventions utilize Bayesian machine learning models to process patient information so as to improve patient outcomes. Bui would have found Thierry’s teaching as Thierry emphasizes in page 1 “Lung cancer constitutes a major public health burden” and thus would benefit from improved treatment protocols.
Regarding claim 2, Bui- Thierry as a combination teaches all of the limitations of claim 1. Thierry also teaches:
receiving a confirmation to implement the recommended treatment; and ([0017] “Figure 1 shows selection of features for a patient for prediction of treatment or treatment efficacy at second evaluation time (t2) (from selected features at t0 and t1) or further evaluation time (t3) (from selected features at t0, t1 and t2)”; see also [0020] "second/further evaluation (time) clinical, biological, genomic and/or radiological feature" refer to all data or features collected after treatment continuation.”
updating the patient data in accordance with the recommended treatment being applied to treat the patient’s medical condition. ([0017] “Figure 1 shows selection of features for a patient for prediction of treatment or treatment efficacy at second evaluation time (t2) (from selected features at t0 and t1) or further evaluation time (t3) (from selected features at t0, t1 and t2).”)
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Bui with the teachings of Thierry, with a reasonable expectation of success, by explicitly using a probabilistic model to calculate a risk score using biological, genomic and radiological information. This would have improved the accuracy of developing a patient’s successful treatment protocol and thus reduce risks on diagnostic protocols. Thierry is adaptable to Bui as both inventions utilize Bayesian machine learning models to process patient information so as to improve patient outcomes. Bui would have found Thierry’s teaching as Thierry emphasizes in page 1 “Lung cancer constitutes a major public health burden” and thus would benefit from improved treatment protocols.
Regarding claim 3, Bui- Thierry as a combination teaches all of the limitations of claim 1. Thierry also teaches
utilizing natural language programming to facilitate interaction with the presented recommended treatment and risk score ([0037] “The machine learning model may be trained within a supervised, semi-supervised or unsupervised learning framework. Within a supervised learning framework, a model learns a function to map an output result from an input data set, based on example pairs of inputs and matching outputs.” See also [0047] “the multimodal data may be obtained or generated from one or more sources… Radiological data may be obtained from Picture Archiving and Communication System (PACS)” comprises natural language programming)
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Bui with the teachings of Thierry, with a reasonable expectation of success, by explicitly using a probabilistic model to calculate a risk score using biological, genomic and radiological information. This would have improved the accuracy of developing a patient’s successful treatment protocol and thus reduce risks on diagnostic protocols. Thierry is adaptable to Bui as both inventions utilize Bayesian machine learning models to process patient information so as to improve patient outcomes. Bui would have found Thierry’s teaching as Thierry emphasizes in page 1 “Lung cancer constitutes a major public health burden” and thus would benefit from improved treatment protocols.
Regarding claim 5, Bui- Thierry as a combination teaches all of the limitations of claim 1. Bui also teaches:
wherein the multimodal model comprises at least one of a visual language model, a large language model, a Bayesian network, a convolutional neural network, graph neural network, or a knowledge graph. ([0137] “Example machine-learned models can include decision tree based models, support vector machines, hidden Markov models, Bayesian networks, linear regression models, k-means clustering models, etc.”)
Regarding claim 7, Bui- Thierry as a combination teaches all of the limitations of claim 1. Thierry also teaches:
wherein the probability model comprises at least one of a visual language model, a large language model, a Bayesian network, a convolutional neural network, graph neural network, or a knowledge graph. ([0037] “Examples of machine learning models used for supervised learning include Support Vector Machines (SVM), regression analysis, linear regression, logistic regression, naive Bayes, linear discriminant analysis, decision trees, k-nearest neighbor algorithms, random forest, artificial neural networks (ANN) such as convolutional neural networks (CNN),”)
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Bui with the teachings of Thierry, with a reasonable expectation of success, by explicitly using a probabilistic model to calculate a risk score using biological, genomic and radiological information. This would have improved the accuracy of developing a patient’s successful treatment protocol and thus reduce risks on diagnostic protocols. Thierry is adaptable to Bui as both inventions utilize Bayesian machine learning models to process patient information so as to improve patient outcomes. Bui would have found Thierry’s teaching as Thierry emphasizes in page 1 “Lung cancer constitutes a major public health burden” and thus would benefit from improved treatment protocols.
Regarding claim 8, Bui- Thierry as a combination teaches all of the limitations of claim 1. Thierry also teaches:
wherein the recommended treatment is a first recommended treatment and the risk score is a first risk score, wherein the operations further comprise: ([0017] “Figure 1 shows selection of features for a patient for prediction of treatment or treatment efficacy at second evaluation time (t2) (from selected features at tO and t1) or further evaluation time (t3) (from selected features at tO, t1 and t2).”; see also [0020] “The terms "first evaluation (time) data", "first evaluation (time) feature", "first evaluation (time) clinical, biological, genomic and/or radiologicals data" or "first evaluation (time) clinical, biological, genomic and/or radiologicals feature" refer to all data or features collected after treatment initiation” where a first evaluation comprises a first recommendation treatment and a first risk score)
generating, based on application of the patient data to the multimodal model, a second recommended treatment, wherein the second recommended treatment is based on at least one node in the sequence of nodes having sufficient similarity to the patient data; ([0185] “2. b) receive separately the patient's multimodal features comprising at least two types of features selected from clinical, biological, genomic and radiological features, wherein the patient's multimodal features are not complete, wherein the patient's at least one multimodal feature is collected at least at two time points, c) aggregate the patient's multimodal features into a vector of features' values, wherein the vector of features' values is not complete,”)
determining a second risk score for the second recommended treatment, wherein the second risk score presents a measure of a successful treatment outcome for the second recommended treatment regarding the patient’s medical condition, wherein the second risk score is determined based on applying the second recommended treatment to a probability model; ([0185] “d) input the vector of features' values to the trained imputation machine learning model and output a complete vector of features' values,”)
ranking the first recommended treatment and the second recommended treatment based on the first risk score and the second risk score; and ([0185] “e) filter the features of the complete vector of features' values according to the list of informative features identifiers and obtain a predictive vector of features' values that is a subset of the complete vector of features' values consisting of filtered features' values,”)
presenting the ranking of the first recommended treatment and first risk score, and the second recommended treatment and the second risk score. ([0185] “f) input the predictive vector of features' values to the trained prediction machine learning model and output prediction of the patient's response to the treatment or prediction of the patient's treatment efficacy defined as length of time to an event.”)
Regarding claim 9, Bui- Thierry as a combination teaches all of the limitations of claim 1. Thierry also teaches:
wherein patient data comprises transcriptomic data pertaining to the medical condition of the patient in combination with at least one of radiology data pertaining to the medical condition of the patient, or pathology data pertaining to the medical condition of the patient. ([0185] “the second machine learning model have been trained to predict patient's treatment response or treatment efficacy using a set of features comprising at least two types of features selected from clinical, biological, genomic and radiological features of cohort of patients having the same disease and receiving the same treatment as the patient for whom the prediction is performed, wherein for each patient in the cohort at least one of the multimodal feature was collected at least at two time points and optionally at least one longitudinal feature was obtained, predicting the patient's treatment response or treatment efficacy.”)
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Bui with the teachings of Thierry, with a reasonable expectation of success, by explicitly using a probabilistic model to calculate a risk score using biological, genomic and radiological information. This would have improved the accuracy of developing a patient’s successful treatment protocol and thus reduce risks on diagnostic protocols. Thierry is adaptable to Bui as both inventions utilize Bayesian machine learning models to process patient information so as to improve patient outcomes. Bui would have found Thierry’s teaching as Thierry emphasizes “Lung cancer constitutes a major public health burden” and thus would benefit from improved treatment protocols.
Regarding claim 10, Bui- Thierry as a combination teaches all of the limitations of claim 9. Thierry also teaches:
wherein the transcriptomic data pertaining to the medical condition of the patient further comprises at least one of proteomic information, single-cell RNA sequencing field (scRNAseq) information, an autofluorescence image, matrix-assisted laser desorption/ionization (MALDI) information, spatial transcriptomic information, multiplexed error-robust fluorescence in situ hybridization (MERFISH), spatial gene expression, or metaboliomic information. ([0047] “Genomic data may be obtained from any system that stores genetic sequences,”)
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Bui with the teachings of Thierry, with a reasonable expectation of success, by explicitly using a probabilistic model to calculate a risk score using biological, genomic and radiological information. This would have improved the accuracy of developing a patient’s successful treatment protocol and thus reduce risks on diagnostic protocols. Thierry is adaptable to Bui as both inventions utilize Bayesian machine learning models to process patient information so as to improve patient outcomes. Bui would have found Thierry’s teaching as Thierry emphasizes “Lung cancer constitutes a major public health burden” and thus would benefit from improved treatment protocols.
Regarding claim 21, Bui teaches:
A computer-implemented method comprising: ([0010] “The method can include obtaining, by a computing system including one or more processors, a search query.”)
receiving, by a system comprising a processor, ([0006] “The system can include one or more processors”) pathomic information comprising pathomic imaging data associated with a set of patients, ([0048] “the systems and methods disclosed herein can allow a computing system to receive a plurality of images of a patient's skin.” comprises receiving pathomic information)
generating, by the system, a multimodal model, wherein generating the multimodal model comprises: combining the pathomic information, radiomic information, and transcriptomic information into a training dataset, ([0089] “The medical conditions classification model may be trained and/or configured for multimodal processing. In some implementations, the medical conditions classification model can process a multimodal query and/or context data to generate the one or more predicted condition classifications… The one or more candidate medical conditions can include skin conditions, hair conditions, infections, cardiovascular conditions, dental conditions, oral conditions, podiatry conditions, genetic conditions, rheumatology conditions, diabetes side effects, blood conditions, cancer classifications, gastrointestinal conditions, trauma conditions, benign cosmetic conditions, eye conditions, and/or other medical condition” comprises receiving information to generate a multimodal model)
and training, using the training dataset, the multimodal model to: [0156] “A set of training data can include a plurality of training instances divided between multiple datasets” and [0159] “Training and/or tuning can include updating the machine-learned model using the evaluation signal.”)
generate a graph using the pathomic information, radiomic information, and transcriptomic information, and recommend treatments for medical conditions of patients based on the graph; ([0196] “The one or more generative models 90 can include … graph generation models… to generate predicted data” see also [0090] “computing system can then provide the annotated image for display with the medical condition information as an output. The annotated image may include annotations generated based on the medical condition information (e.g., label overlays, treatment”)
applying, by the system, patient data to the multimodal model, wherein the patient data pertains to a medical condition of a patient; ([0048] “metadata associated with the patient can also be additionally input into the model… the additional patient metadata can include patient demographic information, medical history, and/or other information concerning the patient (e.g., the user).”)
generating, by the system, based on application of the patient data to the multimodal model, a recommended treatment, ([0048] “the machine-learned skin condition classification model can be configured to jointly process such additional patient metadata alongside the input imagery to produce the output skin condition classification”) wherein the recommended treatment is based on at least one node of the graph having sufficient similarity to the patient data; ([0211] “In general, prediction layers can leverage various kinds of artificial neural networks that can understand or generate sequences of information” and [0196] “The one or more generative models 90 can include … graph generation models… to generate predicted data” see also [0090] “computing system can then provide the annotated image for display with the medical condition information as an output. The annotated image may include annotations generated based on the medical condition information (e.g., label overlays, treatment”)
Regarding claim 21, Bui does not explicitly teach, as taught by Thierry:
receiving… radiomic information comprising radiomic imaging data associated with the set of patients, ([0076] “Radiological data, also referred to as radiomics data, are images collected and include, but are not limited to, computerized tomography (CT)” and [0078] “These images may be acquired from the patient examination”) and transcriptomic information comprising transcriptomic data associated with the set of patients ([0062] “Biological data for the patient may include digital pathology data and proteomic data.” And [0063] The term "genomic data" refers to a digital representation of genomic information, such as a DNA sequence”)
determining, by the system, a risk score for the recommended treatment, wherein the risk score presents a measure of a successful treatment outcome for the recommended treatment regarding the patient's medical condition, wherein the risk score is determined based on applying the recommended treatment to a probability model; ([0015] “a trained prediction machine learning model trained to predict patient's treatment response or treatment efficacy” where the treatment efficacy comprises presenting a measure of a successful treatment outcome for the recommended treatment in the form of a risk score)
and presenting, by the system, the recommended treatment and risk score for review. ([0015] “and output prediction of the patient's response to the treatment or prediction of the patient’s treatment efficacy defined as length of time to an event.”)
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Bui with the teachings of Thierry, with a reasonable expectation of success, by explicitly using a probabilistic model to calculate a risk score using biological, genomic and radiological information. This would have improved the accuracy of developing a patient’s successful treatment protocol and thus reduce risks on diagnostic protocols. Thierry is adaptable to Bui as both inventions utilize Bayesian machine learning models to process patient information so as to improve patient outcomes. Bui would have found Thierry’s teaching as Thierry emphasizes in page 1 “Lung cancer constitutes a major public health burden” and thus would benefit from improved treatment protocols.
Regarding claim 22, Bui-Thierry as a combination teaches all of the limitations of claim 21. Thierry also teaches:
Receiving, by the system, a confirmation to implement the recommended treatment; and ([0017] “Figure 1 shows selection of features for a patient for prediction of treatment efficacy at second evaluation time (t2) (from selected features at t0 and t1) or further evaluation time (t3) (from selected features at t0, t1 and t2)”; see also [0020] "second/further evaluation (time) clinical, biological, genomic and/or radiological feature" refer to all data or features collected after treatment continuation.”
updating, by the system, the patient data in accordance with the recommended treatment being applied to treat the patient’s medical condition. ([0017] “Figure 1 shows selection of features for a patient for prediction of treatment or treatment efficacy at second evaluation time (t2) (from selected features at t0 and t1) or further evaluation time (t3) (from selected features at t0, t1 and t2).”)
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Bui with the teachings of Thierry, with a reasonable expectation of success, by explicitly using a probabilistic model to calculate a risk score using biological, genomic and radiological information. This would have improved the accuracy of developing a patient’s successful treatment protocol and thus reduce risks on diagnostic protocols. Thierry is adaptable to Bui as both inventions utilize Bayesian machine learning models to process patient information so as to improve patient outcomes. Bui would have found Thierry’s teaching as Thierry emphasizes in page 1 “Lung cancer constitutes a major public health burden” and thus would benefit from improved treatment protocols.
Regarding claim 23, Bui- Thierry as a combination teaches all of the limitations of claim 21. Thierry also teaches:
wherein the multimodal model is one of a visual language model, a large language model, graph neural network, or a Bayesian network. ([0137] “Example machine-learned models can include decision tree based models, support vector machines, hidden Markov models, Bayesian networks, linear regression models, k-means clustering models, etc.”)
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Bui with the teachings of Thierry, with a reasonable expectation of success, by explicitly using a probabilistic model to calculate a risk score using biological, genomic and radiological information. This would have improved the accuracy of developing a patient’s successful treatment protocol and thus reduce risks on diagnostic protocols. Thierry is adaptable to Bui as both inventions utilize Bayesian machine learning models to process patient information so as to improve patient outcomes. Bui would have found Thierry’s teaching as Thierry emphasizes in page 1 “Lung cancer constitutes a major public health burden” and thus would benefit from improved treatment protocols.
Regarding claim 24, Bui- Thierry as a combination teaches all of the limitations of claim 21. Thierry also teaches
wherein the patient data comprises transcriptomic data pertaining to the medical condition of the patient in combination with at least one of radiology data pertaining to the medical condition of the patient, or pathology data pertaining to the medical condition of the patient. ([0185] “the second machine learning model have been trained to predict patient's treatment response or treatment efficacy using a set of features comprising at least two types of features selected from clinical, biological, genomic and radiological features of cohort of patients having the same disease and receiving the same treatment as the patient for whom the prediction is performed, wherein for each patient in the cohort at least one of the multimodal feature was collected at least at two time points and optionally at least one longitudinal feature was obtained, predicting the patient's treatment response or treatment efficacy.”)
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Bui with the teachings of Thierry, with a reasonable expectation of success, by explicitly using a probabilistic model to calculate a risk score using biological, genomic and radiological information. This would have improved the accuracy of developing a patient’s successful treatment protocol and thus reduce risks on diagnostic protocols. Thierry is adaptable to Bui as both inventions utilize Bayesian machine learning models to process patient information so as to improve patient outcomes. Bui would have found Thierry’s teaching as Thierry emphasizes “Lung cancer constitutes a major public health burden” and thus would benefit from improved treatment protocols.
Regarding claim 26, Bui teaches:
A computer program product stored on a non-transitory computer-readable medium and comprising machine-executable instructions, wherein, in response to being executed, the machine-executable instructions cause a system to perform operations, comprising: ([0006] “The system can include one or more processors and one or more non-transitory computer-readable media that collectively store instructions that, when executed by the one or more processors, cause the computing system to perform operations”)
receiving pathomic information comprising pathomic imaging data associated with a set of patients, ([0048] “the systems and methods disclosed herein can allow a computing system to receive a plurality of images of a patient's skin.” comprises receiving pathomic information)
generating a multimodal model, wherein generating the multimodal model comprises: combining the pathomic information, radiomic information, and transcriptomic information into a training dataset, ([0089] “The medical conditions classification model may be trained and/or configured for multimodal processing. In some implementations, the medical conditions classification model can process a multimodal query and/or context data to generate the one or more predicted condition classifications… The one or more candidate medical conditions can include skin conditions, hair conditions, infections, cardiovascular conditions, dental conditions, oral conditions, podiatry conditions, genetic conditions, rheumatology conditions, diabetes side effects, blood conditions, cancer classifications, gastrointestinal conditions, trauma conditions, benign cosmetic conditions, eye conditions, and/or other medical condition” comprises receiving information to generate a multimodal model) and training, using the training dataset, the multimodal model to: ([0156] “A set of training data can include a plurality of training instances divided between multiple datasets” and [0159] “Training and/or tuning can include updating the machine-learned model using the evaluation signal.”) generate a graph using the pathomic information, radiomic information, and transcriptomic information, and recommend treatments for medical conditions of patients based on the graph ([0196] “The one or more generative models 90 can include … graph generation models… to generate predicted data” see also [0090] “computing system can then provide the annotated image for display with the medical condition information as an output. The annotated image may include annotations generated based on the medical condition information (e.g., label overlays, treatment”)
applying patient data to the multimodal model, wherein the patient data pertains to a medical condition of a patient; ([0048] “metadata associated with the patient can also be additionally input into the model… the additional patient metadata can include patient demographic information, medical history, and/or other information concerning the patient (e.g., the user).”)
generating, based on application of the patient data to the multimodal model, a recommended treatment, ([0048] “the machine-learned skin condition classification model can be configured to jointly process such additional patient metadata alongside the input imagery to produce the output skin condition classification”) wherein the recommended treatment is based on at least one node of the graph-having sufficient similarity to the patient data; ([0211] “In general, prediction layers can leverage various kinds of artificial neural networks that can understand or generate sequences of information” and [0196] “The one or more generative models 90 can include … graph generation models… to generate predicted data” see also [0090] “computing system can then provide the annotated image for display with the medical condition information as an output. The annotated image may include annotations generated based on the medical condition information (e.g., label overlays, treatment”)
Regarding claim 26, Bui does not explicitly teach, as taught by Thierry:
receiving… radiomic information comprising radiomic imaging data associated with the set of patients, ([0076] “Radiological data, also referred to as radiomics data, are images collected and include, but are not limited to, computerized tomography (CT)” and [0078] “These images may be acquired from the patient examination”) and transcriptomic information comprising transcriptomic data associated with the set of patients ([0062] “Biological data for the patient may include digital pathology data and proteomic data.” And [0063] The term "genomic data" refers to a digital representation of genomic information, such as a DNA sequence”)
determining a risk score for the recommended treatment, wherein the risk score presents a measure of a successful treatment outcome for the recommended treatment regarding the patient's medical condition, wherein the risk score is determined based on applying the recommended treatment to a probability model; ([0015] “a trained prediction machine learning model trained to predict patient's treatment response or treatment efficacy” where the treatment efficacy comprises presenting a measure of a successful treatment outcome for the recommended treatment in the form of a risk score)
and presenting the recommended treatment and risk score for review. ([0015] “and output prediction of the patient's response to the treatment or prediction of the patient's treatment efficacy defined as length of time to an event.”)
Regarding claim 27, Bui- Thierry as a combination teaches all of the limitations of claim 26. Thierry also teaches:
receiving a confirmation to implement the recommended treatment; and ([0017] “Figure 1 shows selection of features for a patient for prediction of treatment or treatment efficacy at second evaluation time (t2) (from selected features at t0 and t1) or further evaluation time (t3) (from selected features at t0, t1 and t2)”; see also [0020] "second/further evaluation (time) clinical, biological, genomic and/or radiological feature" refer to all data or features collected after treatment continuation.”
updating the patient data in accordance with the recommended treatment being applied to treat the patient’s medical condition. ([0017] “Figure 1 shows selection of features for a patient for prediction of treatment or treatment efficacy at second evaluation time (t2) (from selected features at t0 and t1) or further evaluation time (t3) (from selected features at t0, t1 and t2).”)
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Bui with the teachings of Thierry, with a reasonable expectation of success, by explicitly using a probabilistic model to calculate a risk score using biological, genomic and radiological information. This would have improved the accuracy of developing a patient’s successful treatment protocol and thus reduce risks on diagnostic protocols. Thierry is adaptable to Bui as both inventions utilize Bayesian machine learning models to process patient information so as to improve patient outcomes. Bui would have found Thierry’s teaching as Thierry emphasizes in page 1 “Lung cancer constitutes a major public health burden” and thus would benefit from improved treatment protocols.
Regarding claim 28, Bui- Thierry as a combination teaches all of the limitations of claim 26. Thierry also teaches wherein the multimodal model is one of a visual language model, a large language model, graph neural network, or a Bayesian network. ([0137] “Example machine-learned models can include decision tree based models, support vector machines, hidden Markov models, Bayesian networks, linear regression models, k-means clustering models, etc.”)
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Bui with the teachings of Thierry, with a reasonable expectation of success, by explicitly using a probabilistic model to calculate a risk score using biological, genomic and radiological information. This would have improved the accuracy of developing a patient’s successful treatment protocol and thus reduce risks on diagnostic protocols. Thierry is adaptable to Bui as both inventions utilize Bayesian machine learning models to process patient information so as to improve patient outcomes. Bui would have found Thierry’s teaching as Thierry emphasizes in page 1 “Lung cancer constitutes a major public health burden” and thus would benefit from improved treatment protocols.
Regarding claim 29, Bui- Thierry as a combination teaches all of the limitations of claim 26. Thierry also teaches
wherein the patient data comprises transcriptomic data pertaining to the medical condition of the patient in combination with at least one of radiology data pertaining to the medical condition of the patient, or pathology data pertaining to the medical condition of the patient.([0185] “the second machine learning model have been trained to predict patient's treatment response or treatment efficacy using a set of features comprising at least two types of features selected from clinical, biological, genomic and radiological features of cohort of patients having the same disease and receiving the same treatment as the patient for whom the prediction is performed, wherein for each patient in the cohort at least one of the multimodal feature was collected at least at two time points and optionally at least one longitudinal feature was obtained, predicting the patient's treatment response or treatment efficacy.”)
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Bui with the teachings of Thierry, with a reasonable expectation of success, by explicitly using a probabilistic model to calculate a risk score using biological, genomic and radiological information. This would have improved the accuracy of developing a patient’s successful treatment protocol and thus reduce risks on diagnostic protocols. Thierry is adaptable to Bui as both inventions utilize Bayesian machine learning models to process patient information so as to improve patient outcomes. Bui would have found Thierry’s teaching as Thierry emphasizes “Lung cancer constitutes a major public health burden” and thus would benefit from improved treatment protocols.
Claim 4 is rejected under 35 U.S.C. 103 as being unpatentable over Bui et al. (20210065859) in view Thierry et al. (EP4307315) and further in view of Walsh et al. (US20230207124).
Regarding claim 4, Bui- Thierry as a combination teaches all of the limitations of claim 3. Bui- Thierry as a combination does not explicitly teach, as taught by Walsh:
wherein the interaction is via at least one of a mouse and cursor, interactive display, or speech-based interaction. ([0027] “recommendation element 104 may output, e.g., to a classical computing device for display on a display of a computing device, the one or more treatment recommendations with their recommendation scores”; see also [0030] “Classical computing device 202 may include other components not shown in FIG. 2, such input devices, output devices, display screens, a power source, and so on. Communication channel(s) 214 may interconnect each of components 208, 210, and 212 for inter-component communications (physically, communicatively, and/or operatively)” where interactions for the )
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Bui with the teachings of Walsh, with a reasonable expectation of success, by explicitly including a display screen for inter-component communication channels. This would have allowed users to easily input information. Walsh is adaptable to Bui as both inventions use classical computing devices to intake patient information and properly diagnose patients. Bui would have found Walsh’s teaching after researching solutions to avoid any operations that “may increase the risk of misdiagnosis and/or mistreatment” [para 0005].
Claims 6, 25, and 30 are rejected under 35 U.S.C. 103 as being unpatentable over Bui et al. (20210065859) in view Thierry et al. (EP4307315) and further in view of Steven et al. (Pat. 11424011)
Regarding claim 6, Bui- Thierry as a combination teaches all of the limitations of claim 1’s system. Regarding claim 25, Bui- Thierry as a combination teaches all of the limitations of claim 21’s method. Regarding claim 30, Bui- Thierry as a combination teaches all of the limitations of claim 26 product. Regarding claim 6, 25, and 30, Bui-Thierry does not explicitly teach, as taught by Steven:
wherein graph comprises a network of nodes and edges connected to a set of potential treatments, a respective node in the network represents content pertaining to the patient’s medical condition or medical knowledge regarding a medical condition, wherein the medical knowledge pertains or does not pertain to the patient’s medical condition ([Col. 30, lines 55-67] “generating a knowledge graph based at least in part by processing a plurality of documents using one or more natural language processing (NLP) models, wherein: the knowledge graph comprises a plurality of nodes, each respective node corresponding to a respective therapy, and the knowledge graph comprises a plurality of edges indicating comparisons between the therapies; receiving a request to suggest a potential therapy based on a first patient profile”)
It would have been prima facie obvious to a person having ordinary skill in the art to have modified Bui-Thierry with the teachings of Steven, with a reasonable expectation of success, by explicitly generating a knowledge graph comprising nodes and edges that pertain to patient’s medical condition. This would have accurately connected and displayed patient information across multiple datasets for the purposes of diagnosing a patient. Steven is adaptable to Bui as both inventions enable computer-implemented medical decision support systems. Bui would have found Steven’s teaching after researching solutions to the growing knowledge base of references. “With current advancements in medical treatments, alternative, new, or better treatments are becoming available frequently. However, given the rapid pace and complexity of the published literature, it is impossible for healthcare providers to identify and evaluate these potential therapies.” [Col. 1, lines 31-36].
Additional Considerations
The prior art made of record and not relied upon that is considered pertinent to applicant’s disclosure can be found on PTO-892 of the prior office action dated Jan 9, 2026.
Madabhushi et al. (Pat. 11810292) discloses a system for training a machine learning model to generate prognosis of tumor by extracting radiomic features from a tumor.
Rozemberczki, et al. (MOOMIN, CIKM 2022) discloses a deep molecular omics network for Anti-Cancer Drug Combination Therapy.
Conclusion
THIS ACTION IS MADE FINAL. 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 ROBERT ANTHONY SKROBARCZYK whose telephone number is (571)272-3301. The examiner can normally be reached Monday thru Friday 7:30AM -5PM CST.
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, Unsu Jung can be reached at 5712728506. 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.
/R.A.S/Examiner, Art Unit 3792
/KAMBIZ ABDI/Supervisory Patent Examiner, Art Unit 3685
Prosecution Insights