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
This action is in reply to the claims filed on 20 September 2023. Claims 1-20 currently pending and have been examined.
Claim Objections
Claim 18 is objected to because of the following informalities: claim 18 states that is depends from claim 18, itself. This appears to be a typographical error. For the purposes of examination, claim 18 will be considered to depend from claim 17. Appropriate correction is required.
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 USC § 101
Step 1: Is the claim to a process, machine, manufacture, or composition of matter?
Claims 1-20 fall within one or more statutory categories. Claims 1-18 fall within the category of a process. Claim 19 falls within the category of a machine. Claim 20 falls within the category of a manufacture.
Step 2A Prong One: Does the claim recite an abstract idea, law of nature, or natural phenomenon?
Claims 1-20 recite an abstract idea. Representative claim 1 recites:
receiving multi-modal data characterizing a target subject;
generating conditioning data for conditioning the multi-modal data characterizing the target subject based on a population of reference subjects, comprising:
receiving, for each reference subject in the population of reference subjects, a feature representation of the reference subject corresponding to a reference modality and having a plurality of feature dimensions; and
generating the conditioning data based on the feature representations of the reference subjects;
applying the conditioning data to the multi-modal data characterizing the target subject; and
after applying the conditioning data to the multi-modal data characterizing the target subject, … [generating an] output for the target subject.
Therefore, the claim as a whole is directed to “diagnosing a patient,” which is an abstract idea because it is a method of organizing human activity. “Diagnosing a patient” is considered to be a method of organizing human activity because it is an example of managing personal behavior or relationships or interactions between people (including social activities, teaching, and following rules or instructions). The broadest reasonable interpretation of these claim elements, in view of the specification and the dependent claims, includes the collection, interpretation, and analysis of a patient by a healthcare provider.
Alternatively, the claims are directed to a mental process because they include concepts capable of being performed in the human mind (including an observation, evaluation, judgment, opinion).
Step 2A Prong Two: Does the claim recite additional elements that integrate the judicial exception into a practical application?
This judicial exception is not integrated into a practical application. In particular, claim 1 recites the following additional element(s):
[the method is] performed by one or more computers;
processing the multi-modal data characterizing the target subject using a machine learning model to generate a machine learning model output.
The additional elements individually or in combination do not integrate the exception into a practical application. These additional elements merely recite the words ‘‘apply it’’ (or an equivalent) with the judicial exception, or merely include instructions to implement an abstract idea on a computer, or merely use a computer as a tool to perform an abstract idea (see MPEP 2106.05(f)). Accordingly, these additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. Claim 1 is directed to an abstract idea.
Step 2B: Does the claim recite additional elements that amount to significantly more than the judicial exception?
Claim 1 does not include additional elements, considered individually or in combination, that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional element(s), individually and in combination, merely recite the words ‘‘apply it’’ (or an equivalent) with the judicial exception, or merely include instructions to implement an abstract idea on a computer, or merely use a computer as a tool to perform an abstract idea (see MPEP 2106.05(f)). Accordingly, claim 1 is ineligible.
Dependent claim 2 recites the method of claim 1, wherein:
generating the conditioning data based on the feature representations of the reference subjects
comprises:
determining, for each pair of feature dimensions comprising a first feature dimension and a second feature dimension from the plurality of feature dimensions, a respective correlation coefficient for the pair of feature dimensions that measures a correlation between:
(i) a value of the first feature dimension in the feature representations of the reference subjects, and
(ii) a value of the second feature dimension in the feature representations of the reference subjects; and
generating the conditioning data based on the correlation coefficients.
These elements recite another abstract idea in the form of a mathematical process, that of a mathematical calculation. This merely further limits the abstract idea of claim 1 discussed above and does not provide further additional elements. Therefore, claim 2 is considered to be ineligible.
Dependent claim 3 recites the method of claim 2, wherein:
for each reference subject in the population of reference subjects:
the plurality of feature dimensions in the feature representation of the reference subject comprise a respective feature dimension corresponding to each protein in a predefined set of proteins and
the value of each feature dimension corresponding to a protein defines an expression level of the protein in the reference subject.
This merely further limits the abstract idea of claim 1 discussed above and does not provide further additional elements. Therefore, claim 3 is considered to be ineligible.
Dependent claim 4 recites the method of claim 2, wherein:
for each reference subject in the population of reference subjects:
the plurality of feature dimensions in the feature representation of the reference subject comprise a respective feature dimension corresponding to each gene in a predefined set of genes; and
the value of each feature dimension corresponding to a gene defines an expression level of the gene in the reference subject.
This merely further limits the abstract idea of claim 1 discussed above and does not provide further additional elements. Therefore, claim 4 is considered to be ineligible.
Dependent claim 5 recites the method of claim 1, comprising:
receiving, for each reference subject in the population of reference subjects, a label that defines:
(i) whether the reference subject has a particular medical condition, or
(ii) whether the reference subject has responded to a treatment for a particular medical condition;
wherein generating the conditioning data based on the feature representations of the reference subjects comprises: determining, for each feature dimension from the plurality of feature dimensions, a respective correlation coefficient that measures a correlation between:
(i) a value of the feature dimension in the feature representations of the reference subjects, and
(ii) the labels of the reference subjects; and
generating the condition data based on the correlation coefficients.
These elements recite another abstract idea in the form of a mathematical process, that of a mathematical calculation. This merely further limits the abstract idea of claim 1 discussed above and does not provide further additional elements. Therefore, claim 5 is considered to be ineligible.
Dependent claim 6 recites the method of claim 1, wherein:
for each reference subject in the population of reference subjects, receiving a feature representation of the reference subject corresponding to a reference modality comprises:
receiving a pre-treatment feature representation of the reference subject captured before a medical treatment is applied to the reference subject; and
receiving a post-treatment feature representation of the reference subject captured after the medical treatment is applied to the reference subject.
This merely further limits the abstract idea of claim 1 discussed above and does not provide further additional elements. Therefore, claim 6 is considered to be ineligible.
Dependent claim 7 recites the method of claim 1, wherein:
generating the conditioning data based on the feature representations of the reference subjects comprises:
generating, for each reference subject, a differential feature representation of the reference subject as a difference between: (i) the pre-treatment feature representation of the reference subject, and (ii) the post-treatment feature representation of the reference subject;
generating the conditioning data as a combination of the differential feature representations of the reference subjects.
The additional elements present in this claim merely recite the words ‘‘apply it’’ (or an equivalent) with the judicial exception, or merely includes instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea (see MPEP 2106.05(f)). These types of additional elements are not enough to integrate the abstract idea into a practical application, nor do they amount to significantly more than the judicial exception. Accordingly, claim 7 is ineligible.
Dependent claim 8 recites the method of claim 7, wherein:
generating the conditioning data as a combination of the differential feature representations of reference subjects comprises:
generating the conditioning data as an average of the differential feature representations of the reference subjects.
The additional elements present in this claim merely recite the words ‘‘apply it’’ (or an equivalent) with the judicial exception, or merely includes instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea (see MPEP 2106.05(f)). These types of additional elements are not enough to integrate the abstract idea into a practical application, nor do they amount to significantly more than the judicial exception. Accordingly, claim 8 is ineligible.
Dependent claim 9 recites the method of claim 6, wherein:
the pre-treatment feature representation and the post- treatment feature representation of the reference subject are captured using functional magnetic resonance imaging (fMRI).
This merely further limits the abstract idea of claim 1 discussed above and does not provide further additional elements. Therefore, claim 9 is considered to be ineligible.
Dependent claim 10 recites the method of claim 6, wherein:
the pre-treatment feature representation and the post- treatment feature representation of the reference subject are captured using positron emission tomography (PET) imaging.
This merely further limits the abstract idea of claim 1 discussed above and does not provide further additional elements. Therefore, claim 10 is considered to be ineligible.
Dependent claim 11 recites the method of claim 1, wherein:
applying the conditioning data to the multi-modal data characterizing the target subject comprises: pointwise multiplying each of a plurality of feature dimensions of the multi-modal data by a corresponding dimension of the conditioning data.
These elements recite another abstract idea in the form of a mathematical process, that of a mathematical calculation. This merely further limits the abstract idea of claim 1 discussed above and does not provide further additional elements. Therefore, claim 11 is considered to be ineligible.
Dependent claim 12 recites the method of claim 1, wherein:
the conditioning data is represented as a two-dimensional (2D) matrix of numerical values, and
wherein applying the conditioning data to the multi-modal data characterizing the target subject comprises: matrix multiplying a plurality of feature dimensions of the multi-modal data by the 2D matrix of numerical values representing the conditioning data.
These elements recite another abstract idea in the form of a mathematical process, that of a mathematical calculation. This merely further limits the abstract idea of claim 1 discussed above and does not provide further additional elements. Therefore, claim 12 is considered to be ineligible.
Dependent claim 13 recites the method of claim 1, wherein:
applying the conditioning data to the multi-modal data characterizing the target subject comprises: applying the conditioning data to a plurality of feature dimensions of the multi-modal data corresponding to a target modality,
wherein the target modality is a different modality than the reference modality used to generate the conditioning data.
This merely further limits the abstract idea of claim 1 discussed above and does not provide further additional elements. Therefore, claim 13 is considered to be ineligible.
Dependent claim 14 recites the method of claim 1, wherein:
the machine learning model comprises an encoder neural network, and
wherein processing the multi-modal data characterizing the target subject using the machine learning model comprises:
processing the multi-modal data characterizing the target subject using the encoder neural network to generate an embedding of the multi-modal data characterizing the target subject;
determining a respective classification score for each patient category in a set of patient categories based on the embedding of the multi-modal data characterizing the target subject; and
classifying the target subject as being included in a corresponding patient category from the set of patient categories based on the classification scores.
The additional elements present in this claim merely recite the words ‘‘apply it’’ (or an equivalent) with the judicial exception, or merely includes instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea (see MPEP 2106.05(f)). These types of additional elements are not enough to integrate the abstract idea into a practical application, nor do they amount to significantly more than the judicial exception. Accordingly, claim 14 is ineligible.
Dependent claim 15 recites the method of claim 1, wherein:
processing the multi-modal data characterizing the target subject using the machine learning model comprises: processing the multi-modal data characterizing the target subject using the machine learning model, in accordance with values of a plurality of machine learning model parameters, to generate a prediction characterizing the target subject.
The additional elements present in this claim merely recite the words ‘‘apply it’’ (or an equivalent) with the judicial exception, or merely includes instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea (see MPEP 2106.05(f)). These types of additional elements are not enough to integrate the abstract idea into a practical application, nor do they amount to significantly more than the judicial exception. Accordingly, claim 15 is ineligible.
Dependent claim 16 recites the method of claim 15, wherein:
the prediction characterizing the target subject comprises a prediction for whether the target subject has a particular medical condition.
This merely further limits the abstract idea of claim 1 discussed above and does not provide further additional elements. Therefore, claim 16 is considered to be ineligible.
Dependent claim 17 recites the method of claim 1, wherein:
the multi-modal data characterizing the target subject comprises a respective feature representation for each of a plurality of modalities.
This merely further limits the abstract idea of claim 1 discussed above and does not provide further additional elements. Therefore, claim 17 is considered to be ineligible.
Dependent claim 18 recites the method of claim 17, wherein:
each of the plurality of modalities corresponds to a respective sensor, and
wherein the feature representation of each modality is based on data generated by the corresponding sensor.
This merely further limits the abstract idea of claim 1 discussed above and does not provide further additional elements. Therefore, claim 18 is considered to be ineligible.
Claim 19 is parallel in nature to claim 1. Accordingly claim 19 is rejected as being directed towards ineligible subject matter based upon the same analysis above.
Claim 20 is parallel in nature to claim 1. Accordingly claim 20 is rejected as being directed towards ineligible subject matter based upon the same analysis above.
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 1-2 and 11-20 are rejected under 35 U.S.C. 103 as being unpatentable over Mastoridis et al. (U.S. 2022/0181023), hereinafter “Mastoridis,” in view of Ghosal et al., "G-MIND: an end-to-end multimodal imaging-genetics framework for biomarker identification and disease classification", Proc. SPIE 11596, Medical Imaging 2021: Image Processing, 115960C (15 Feb 2021), hereinafter “Ghosal.”
Regarding Claim 1, Mastoridis discloses a method performed by one or more computers, the method comprising:
receiving [patient] data characterizing a target subject (See Mastoridis [0098] system receives a set of patient data corresponding to a patient. The set of patient data includes a plurality of data inputs representing the patient's features, physiological measurements, and/or other information relevant to diagnosing asthma and/or COPD.);
generating conditioning data for conditioning the multi-modal data characterizing the target subject (See Mastoridis [0055] Feature engineering and data conditioning. System includes adding the one or more new data inputs for the one or more patients to the data set after calculating the values for the one or more new data inputs.) based on a population of reference subjects (See Mastoridis [0059] system could have calculated the values for the new data inputs based on (1) the values of one or more data inputs of the plurality of data inputs for each of the plurality of patients, (2) existing models available within relevant research and/or academic literature, and/or (3) patient age and/or gender matched averages.), comprising:
receiving, for each reference subject in the population of reference subjects, a feature representation of the reference subject corresponding to a reference modality and having a plurality of feature dimensions (See Mastoridis [0047] the system uses patient population data with data inputs that represent patient features, physiological measurements, and other information relevant to diagnosing asthma and/or COPD., including a diagnosis of asthma and/or COPD for each of the plurality of patients.); and
generating the conditioning data based on the feature representations of the reference subjects (See Mastoridis [0055] Feature engineering and data conditioning. System includes adding the one or more new data inputs for the one or more patients to the data set after calculating the values for the one or more new data inputs. [0059] system could have calculated the values for the new data inputs based on (1) the values of one or more data inputs of the plurality of data inputs for each of the plurality of patients, (2) existing models available within relevant research and/or academic literature, and/or (3) patient age and/or gender matched averages.);
applying the conditioning data to the multi-modal data characterizing the target subject (See Mastoridis [0055] Feature engineering and data conditioning. System includes adding the one or more new data inputs for the one or more patients to the data set after calculating the values for the one or more new data inputs. [0059] system could have calculated the values for the new data inputs based on (1) the values of one or more data inputs of the plurality of data inputs for each of the plurality of patients, (2) existing models available within relevant research and/or academic literature, and/or (3) patient age and/or gender matched averages.); and
after applying the conditioning data to the multi-modal data characterizing the target subject (See Mastoridis [0055] Feature engineering and data conditioning. System includes adding the one or more new data inputs for the one or more patients to the data set after calculating the values for the one or more new data inputs.), processing the [patient] data characterizing the target subject using a machine learning model to generate a machine learning model output for the target subject (See Mastoridis Fig. 10 and [0120]-[0121] system uses machine learning to analyze patient data that has been conditioned and generate a diagnosis.).
Mastoridis does not disclose:
[the patient data is] multimodal.
Ghosal teaches:
[the patient data is] multimodal (See Ghosal Introduction, page 2; the system uses multimodal imaging and genetic data along with neural network designs to make patient predictions.).
The system of Ghosal is applicable to the disclosure of Mastoridis as they both share characteristics and capabilities, namely, they are directed to using neural networks to analyze patient data using conditioning data. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Mastoridis to include multimodal data and classification techniques as taught by Ghosal. One of ordinary skill in the art before the effective filing date of the claimed invention would have been motivated to modify Mastoridis in order to achieve better classification accuracy than baseline methods, and generalize to a second dataset collected at a different site (see Ghosal Abstract).
Regarding claim 2, Mastoridis in view of Ghosal discloses the method of claim 1 as discussed above. Mastoridis further discloses a method, wherein:
generating the conditioning data based on the feature representations of the reference subjects (See Mastoridis [0055] Feature engineering and data conditioning. System includes adding the one or more new data inputs for the one or more patients to the data set after calculating the values for the one or more new data inputs.) comprises:
determining, for each pair of feature dimensions comprising a first feature dimension and a second feature dimension from the plurality of feature dimensions, a respective correlation coefficient for the pair of feature dimensions (See Mastoridis [0065] Each generated cluster of patients of the one or more generated clusters of patients includes two or more patients having similar/correlated reduced-dimension representations of their data input values (e.g., similar/correlated coordinates). [0067] system uses a correlation requirements between different features in the data set. [0084] system uses Pearson correlation filtering to perform feature engineering and feature selection.) that measures a correlation between:
(i) a value of the first feature dimension in the feature representations of the reference subjects (See Mastoridis [0065] Each generated cluster of patients of the one or more generated clusters of patients includes two or more patients having similar/correlated reduced-dimension representations of their data input values (e.g., similar/correlated coordinates). [0067] system uses a correlation requirements between different features in the data set.), and
(ii) a value of the second feature dimension in the feature representations of the reference subjects (See Mastoridis [0065] Each generated cluster of patients of the one or more generated clusters of patients includes two or more patients having similar/correlated reduced-dimension representations of their data input values (e.g., similar/correlated coordinates). [0067] system uses a correlation requirements between different features in the data set.); and
generating the conditioning data based on the correlation coefficients (See Mastoridis [0084] system uses Pearson correlation filtering to perform feature engineering and feature selection.).
Regarding claim 11, Mastoridis in view of Ghosal discloses the method of claim 1 as discussed above. Mastoridis does not further disclose a method, wherein:
applying the conditioning data to the multi-modal data characterizing the target subject comprises: pointwise multiplying each of a plurality of feature dimensions of the multi-modal data by a corresponding dimension of the conditioning data.
Ghosal teaches:
applying the conditioning data to the multi-modal data characterizing the target subject comprises: pointwise multiplying each of a plurality of feature dimensions of the multi-modal data by a corresponding dimension of the conditioning data 9See Ghosal Section 2.5, page 4; the system multiplies the conditioning data on the available modalities. Therefore, it is understood that the system is performing matrix multiplication on the 2D representation of patient features.).
The system of Ghosal is applicable to the disclosure of Mastoridis as they both share characteristics and capabilities, namely, they are directed to using neural networks to analyze patient data using conditioning data. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Mastoridis to include multimodal data and classification techniques as taught by Ghosal. One of ordinary skill in the art before the effective filing date of the claimed invention would have been motivated to modify Mastoridis in order to achieve better classification accuracy than baseline methods, and generalize to a second dataset collected at a different site (see Ghosal Abstract).
Regarding claim 12, Mastoridis in view of Ghosal discloses the method of claim 1 as discussed above. Mastoridis further discloses a method, wherein:
the conditioning data is represented as a two-dimensional (2D) matrix of numerical values (See Mastoridis [0062] the system uses two dimensional representations of the data as input for the machine learning model.).
Mastoridis does not disclose:
wherein applying the conditioning data to the multi-modal data characterizing the target subject comprises: matrix multiplying a plurality of feature dimensions of the multi-modal data by the 2D matrix of numerical values representing the conditioning data.
Ghosal teaches:
wherein applying the conditioning data to the multi-modal data characterizing the target subject comprises: matrix multiplying a plurality of feature dimensions of the multi-modal data by the 2D matrix of numerical values representing the conditioning data (See Ghosal Section 2.5, page 4; the system multiplies the conditioning data on the available modalities. Therefore, it is understood that the system is performing matrix multiplication on the 2D representation of patient features.).
The system of Ghosal is applicable to the disclosure of Mastoridis as they both share characteristics and capabilities, namely, they are directed to using neural networks to analyze patient data using conditioning data. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Mastoridis to include multimodal data and classification techniques as taught by Ghosal. One of ordinary skill in the art before the effective filing date of the claimed invention would have been motivated to modify Mastoridis in order to achieve better classification accuracy than baseline methods, and generalize to a second dataset collected at a different site (see Ghosal Abstract).
Regarding claim 13, Mastoridis in view of Ghosal discloses the method of claim 1 as discussed above. Mastoridis further discloses a method, wherein:
applying the conditioning data to the multi-modal data characterizing the target subject comprises: applying the conditioning data to a plurality of feature dimensions of the multi-modal data corresponding to a target modality (See Mastoridis [0055] Feature engineering and data conditioning. System includes adding the one or more new data inputs for the one or more patients to the data set after calculating the values for the one or more new data inputs. [0089] the system includes data from a first plurality of patients having one or more phenotypic differences regarding patient features and/or one or more respiratory conditions.).
Mastoridis does not disclose:
wherein the target modality is a different modality than the reference modality used to generate the conditioning data.
Ghosal teaches:
wherein the target modality is a different modality than the reference modality used to generate the conditioning data (See Ghosal Section 2.5, page 4; the system multiplies the conditioning data on the available modalities. Therefore, the modalities can be different between available and unavailable data sets used for the machine learning prediction.).
The system of Ghosal is applicable to the disclosure of Mastoridis as they both share characteristics and capabilities, namely, they are directed to using neural networks to analyze patient data using conditioning data. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Mastoridis to include multimodal data and classification techniques as taught by Ghosal. One of ordinary skill in the art before the effective filing date of the claimed invention would have been motivated to modify Mastoridis in order to achieve better classification accuracy than baseline methods, and generalize to a second dataset collected at a different site (see Ghosal Abstract).
Regarding claim 14, Mastoridis in view of Ghosal discloses the method of claim 1 as discussed above. Mastoridis further discloses a method, wherein:
the machine learning model comprises an encoder neural network (See Mastoridis [0041] A machine learning algorithm can be implemented using a variety of techniques, including the use of one or more of an artificial neural network, a deep neural network, a convolutional neural network, a multilayer perceptron, and the like., and
wherein processing the multi-modal data characterizing the target subject using the machine learning model comprises: processing the multi-modal data characterizing the target subject using the encoder neural network (See Mastoridis [0041] A machine learning algorithm can be implemented using a variety of techniques, including the use of one or more of an artificial neural network, a deep neural network, a convolutional neural network, a multilayer perceptron, and the like.) to generate an embedding of the multi-modal data characterizing the target subject (See Mastoridis [0126] In some examples, in addition to outputting the confidence scores, the computing system outputs (e.g., displays on a display) a visual breakdown of one or more confidence scores that the computing system outputs (e.g., a visual breakdown for each confidence score). A visual breakdown of a confidence score represents how the computing system generated the confidence score by showing the most impactful data input values with respect to the computing system's determination of a corresponding predicted asthma and/or COPD diagnosis (e.g., showing how those data input values push towards or away from the predicted diagnosis).);
determining a respective classification score for each patient category in a set of patient categories based on the embedding of the multi-modal data characterizing the target subject (See Mastoridis [0126] In some examples, in addition to outputting the confidence scores, the computing system outputs (e.g., displays on a display) a visual breakdown of one or more confidence scores that the computing system outputs (e.g., a visual breakdown for each confidence score). A visual breakdown of a confidence score represents how the computing system generated the confidence score by showing the most impactful data input values with respect to the computing system's determination of a corresponding predicted asthma and/or COPD diagnosis (e.g., showing how those data input values push towards or away from the predicted diagnosis).); and
classifying the target subject as being included in a corresponding patient category from the set of patient categories based on the classification scores (See Mastoridis [0126] In some examples, in addition to outputting the confidence scores, the computing system outputs (e.g., displays on a display) a visual breakdown of one or more confidence scores that the computing system outputs (e.g., a visual breakdown for each confidence score). A visual breakdown of a confidence score represents how the computing system generated the confidence score by showing the most impactful data input values with respect to the computing system's determination of a corresponding predicted asthma and/or COPD diagnosis (e.g., showing how those data input values push towards or away from the predicted diagnosis).).
Regarding claim 15, Mastoridis in view of Ghosal discloses the method of claim 1 as discussed above. Mastoridis further discloses a method, wherein:
processing the multi-modal data characterizing the target subject using the machine learning model comprises: processing the multi-modal data characterizing the target subject using the machine learning model, in accordance with values of a plurality of machine learning model parameters, to generate a prediction characterizing the target subject (See Mastoridis Fig. 10 and [0120]-[0121] system uses machine learning to analyze patient data that has been conditioned and generate a diagnosis.).
Regarding claim 16, Mastoridis in view of Ghosal discloses the method of claim 15 as discussed above. Mastoridis further discloses a method, wherein:
the prediction characterizing the target subject comprises a prediction for whether the target subject has a particular medical condition (See Mastoridis Fig. 10 and [0120]-[0121] system uses machine learning to analyze patient data that has been conditioned and generate a diagnosis.).
Regarding claim 17, Mastoridis in view of Ghosal discloses the method of claim 1 as discussed above. Mastoridis does not further disclose a method, wherein:
the multi-modal data characterizing the target subject comprises a respective feature representation for each of a plurality of modalities.
Ghosal teaches:
the multi-modal data characterizing the target subject comprises a respective feature representation for each of a plurality of modalities (See Ghosal Introduction, page 2; the system uses multimodal imaging and genetic data along with neural network designs to make patient predictions.).
The system of Ghosal is applicable to the disclosure of Mastoridis as they both share characteristics and capabilities, namely, they are directed to using neural networks to analyze patient data using conditioning data. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Mastoridis to include multimodal data and classification techniques as taught by Ghosal. One of ordinary skill in the art before the effective filing date of the claimed invention would have been motivated to modify Mastoridis in order to achieve better classification accuracy than baseline methods, and generalize to a second dataset collected at a different site (see Ghosal Abstract).
Regarding claim 18, Mastoridis in view of Ghosal discloses the method of claim 17 as discussed above. Mastoridis further discloses a method, wherein:
each of the plurality of modalities corresponds to a respective sensor (See Mastoridis [0098] he data inputs representing the patient's physiological measurements includes results of at least one physiological test administered to the patient (e.g., a lung function test, an exhaled nitric oxide test (such as a FeNO test). Some examples of such physiological test devices include (but are not limited to) a spirometry device, a FeNO device, and a chest radiography (x-ray) device.), and
wherein the feature representation of each modality is based on data generated by the corresponding sensor (See Mastoridis [0098] The set of patient data includes a plurality of data inputs representing the patient's features, physiological measurements, and/or other information relevant to diagnosing asthma and/or COPD.).
Regarding claim 19, Mastoridis in view of Ghosal discloses the method of claim 1 as discussed above. Claim 19 recites a system that performs a method that is substantially similar to the method of claim 1. Accordingly, claim 19 is rejected based on the same analysis.
Regarding claim 20, Mastoridis in view of Ghosal discloses the method of claim 1 as discussed above. Claim 20 recites a medium storing a method that is substantially similar to the method of claim 1. Accordingly, claim 20 is rejected based on the same analysis.
Claims 3-10 are rejected under 35 U.S.C. 103 as being unpatentable over Mastoridis et al. (U.S. 2022/0181023), hereinafter “Mastoridis,” in view of Ghosal et al., "G-MIND: an end-to-end multimodal imaging-genetics framework for biomarker identification and disease classification", Proc. SPIE 11596, Medical Imaging 2021: Image Processing, 115960C (15 Feb 2021), hereinafter “Ghosal,” and further in view of Lipsky et al. (U.S. 2021/0104321), hereinafter “Lipsky.”
Regarding claim 3, Mastoridis in view of Ghosal discloses the method of claim 2 as discussed above. Mastoridis does not further discloses a method, wherein:
for each reference subject in the population of reference subjects: the plurality of feature dimensions in the feature representation of the reference subject comprise a respective feature dimension corresponding to each protein in a predefined set of proteins; and
the value of each feature dimension corresponding to a protein defines an expression level of the protein in the reference subject.
Lipsky teaches:
for each reference subject in the population of reference subjects: the plurality of feature dimensions in the feature representation of the reference subject comprise a respective feature dimension corresponding to each protein in a predefined set of proteins (See Lipsky [0338] system uses machine learning to correlate genetic records and patient phenotypes. [0341] the records used by the system include proteome data (i.e. protein expression). See also [0112].); and
the value of each feature dimension corresponding to a protein defines an expression level of the protein in the reference subject (See Lipsky [0338] system uses machine learning to correlate genetic records and patient phenotypes. [0341] the records used by the system include proteome data (i.e. protein expression). See also [0112].).
The system of Lipsky is applicable to the disclosure of Mastoridis in view of Ghosal as they both share characteristics and capabilities, namely, they are directed to . It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Mastoridis to include proteomic, transcriptomic, and treatment outcome data as taught by Lipsky. One of ordinary skill in the art before the effective filing date of the claimed invention would have been motivated to modify Mastoridis in order to quickly and effectively identify genetic and phenotypic features (see Lipsky [0002]).
Regarding claim 4, Mastoridis in view of Ghosal discloses the method of claim 2 as discussed above. Mastoridis does nor further disclose a method, wherein:
for each reference subject in the population of reference subjects: the plurality of feature dimensions in the feature representation of the reference subject comprise a respective feature dimension corresponding to each gene in a predefined set of genes; and
the value of each feature dimension corresponding to a gene defines an expression level of the gene in the reference subject.
Lipsky teaches:
for each reference subject in the population of reference subjects: the plurality of feature dimensions in the feature representation of the reference subject comprise a respective feature dimension corresponding to each gene in a predefined set of genes (See Lipsky [0338] system uses machine learning to correlate genetic records and patient phenotypes. [0341] the records used by the system include transcriptome data (i.e. gene expression data). See also [0112].); and
the value of each feature dimension corresponding to a gene defines an expression level of the gene in the reference subject (See Lipsky [0338] system uses machine learning to correlate genetic records and patient phenotypes. [0341] the records used by the system include transcriptome data (i.e. gene expression data). See also [0112].).
The system of Lipsky is applicable to the disclosure of Mastoridis in view of Ghosal as they both share characteristics and capabilities, namely, they are directed to . It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Mastoridis to include proteomic, transcriptomic, and treatment outcome data as taught by Lipsky. One of ordinary skill in the art before the effective filing date of the claimed invention would have been motivated to modify Mastoridis in order to quickly and effectively identify genetic and phenotypic features (see Lipsky [0002]).
Regarding claim 5, Mastoridis in view of Ghosal discloses the method of claim 1 as discussed above. Mastoridis further discloses a method, comprising:
receiving, for each reference subject in the population of reference subjects, a label that defines: (i) whether the reference subject has a particular medical condition (See Mastoridis [0047] The electronic health records used by the system include a diagnosis of asthma and/or COPD for each of the plurality of patients.), or
wherein generating the conditioning data based on the feature representations of the reference subjects comprises: determining, for each feature dimension from the plurality of feature dimensions, a respective correlation coefficient (See Mastoridis [0084] system uses Pearson correlation filtering to perform feature engineering and feature selection.) that measures a correlation between:
(i) a value of the feature dimension in the feature representations of the reference subjects (See Mastoridis [0065] Each generated cluster of patients of the one or more generated clusters of patients includes two or more patients having similar/correlated reduced-dimension representations of their data input values (e.g., similar/correlated coordinates). [0067] system uses a correlation requirements between different features in the data set.), and
(ii) the labels of the reference subjects (See Mastoridis [0065] Each generated cluster of patients of the one or more generated clusters of patients includes two or more patients having similar/correlated reduced-dimension representations of their data input values (e.g., similar/correlated coordinates). [0067] system uses a correlation requirements between different features in the data set.); and
generating the condition data based on the correlation coefficients (See Mastoridis [0084] system uses Pearson correlation filtering to perform feature engineering and feature selection.).
Mastoridis does not disclose:
a label that defines: (ii) whether the reference subject has responded to a treatment for a particular medical condition.
Lipsky teaches:
a label that defines: (ii) whether the reference subject has responded to a treatment for a particular medical condition (See Lipsky [0513] the system can use PET imaging for confirm the efficacy of the course of treatment for treating the condition. It is understood that this means there is pre and post treatment PET scans of the patient.).
The system of Lipsky is applicable to the disclosure of Mastoridis in view of Ghosal as they both share characteristics and capabilities, namely, they are directed to . It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Mastoridis to include proteomic, transcriptomic, and treatment outcome data as taught by Lipsky. One of ordinary skill in the art before the effective filing date of the claimed invention would have been motivated to modify Mastoridis in order to quickly and effectively identify genetic and phenotypic features (see Lipsky [0002]).
Regarding claim 6, Mastoridis in view of Ghosal discloses the method of claim 1 as discussed above. Mastoridis does not further disclose a method, wherein:
for each reference subject in the population of reference subjects, receiving a feature representation of the reference subject corresponding to a reference modality comprises:
receiving a pre-treatment feature representation of the reference subject captured before a medical treatment is applied to the reference subject; and
receiving a post-treatment feature representation of the reference subject captured after the medical treatment is applied to the reference subject.
Lipsky teaches:
for each reference subject in the population of reference subjects, receiving a feature representation of the reference subject corresponding to a reference modality (See Lipsky [0513] the system can use PET imaging for confirm the efficacy of the course of treatment for treating the condition. It is understood that this means there is pre and post treatment PET scans of the patient.) comprises:
receiving a pre-treatment feature representation of the reference subject captured before a medical treatment is applied to the reference subject (See Lipsky [0513] the system can use PET imaging for confirm the efficacy of the course of treatment for treating the condition. It is understood that this means there is pre and post treatment PET scans of the patient.); and
receiving a post-treatment feature representation of the reference subject captured after the medical treatment is applied to the reference subject (See Lipsky [0513] the system can use PET imaging for confirm the efficacy of the course of treatment for treating the condition. It is understood that this means there is pre and post treatment PET scans of the patient.).
The system of Lipsky is applicable to the disclosure of Mastoridis in view of Ghosal as they both share characteristics and capabilities, namely, they are directed to . It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Mastoridis to include proteomic, transcriptomic, and treatment outcome data as taught by Lipsky. One of ordinary skill in the art before the effective filing date of the claimed invention would have been motivated to modify Mastoridis in order to quickly and effectively identify genetic and phenotypic features (see Lipsky [0002]).
Regarding claim 7, Mastoridis in view of Ghosal and Lipsky discloses the method of claim 6 as discussed above. Mastoridis further discloses a method, wherein:
generating the conditioning data based on the feature representations of the reference subjects (See Mastoridis [0055] Feature engineering and data conditioning. System includes adding the one or more new data inputs for the one or more patients to the data set after calculating the values for the one or more new data inputs.) comprises:
generating, for each reference subject, a differential feature representation of the reference subject as a difference between: [different variables] (See Mastoridis [0089] the system includes data from a first plurality of patients having one or more phenotypic differences regarding patient features and/or one or more respiratory conditions.);
generating the conditioning data as a combination of the differential feature representations of the reference subjects (See Mastoridis [0055] Feature engineering and data conditioning. System includes adding the one or more new data inputs for the one or more patients to the data set after calculating the values for the one or more new data inputs. [0089] the system includes data from a first plurality of patients having one or more phenotypic differences regarding patient features and/or one or more respiratory conditions.).
Mastoridis does not disclose:
[the different variables are] (i) the pre-treatment feature representation of the reference subject, and
(ii) the post-treatment feature representation of the reference subject.
Lipsky teaches:
[the different variables are] (i) the pre-treatment feature representation of the reference subject (See Lipsky [0513] the system can use PET imaging for confirm the efficacy of the course of treatment for treating the condition. It is understood that this means there is pre and post treatment PET scans of the patient.), and
(ii) the post-treatment feature representation of the reference subject (See Lipsky [0513] the system can use PET imaging for confirm the efficacy of the course of treatment for treating the condition. It is understood that this means there is pre and post treatment PET scans of the patient.).
The system of Lipsky is applicable to the disclosure of Mastoridis in view of Ghosal as they both share characteristics and capabilities, namely, they are directed to . It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Mastoridis to include proteomic, transcriptomic, and treatment outcome data as taught by Lipsky. One of ordinary skill in the art before the effective filing date of the claimed invention would have been motivated to modify Mastoridis in order to quickly and effectively identify genetic and phenotypic features (see Lipsky [0002]).
Regarding claim 8, Mastoridis in view of Ghosal and Lipsky discloses the method of claim 7 as discussed above. Mastoridis further discloses a method, wherein:
generating the conditioning data as a combination of the differential feature representations of reference subjects (See Mastoridis [0055] Feature engineering and data conditioning. System includes adding the one or more new data inputs for the one or more patients to the data set after calculating the values for the one or more new data inputs. [0089] the system includes data from a first plurality of patients having one or more phenotypic differences regarding patient features and/or one or more respiratory conditions.) comprises:
generating the conditioning data as an average of the differential feature representations of the reference subjects (See Mastoridis [0059] system could have calculated the values for the new data inputs based on (1) the values of one or more data inputs of the plurality of data inputs for each of the plurality of patients, (2) existing models available within relevant research and/or academic literature, and/or (3) patient age and/or gender matched averages.).
Regarding claim 9, Mastoridis in view of Ghosal and Lipsky discloses the method of claim 6 as discussed above. Mastoridis does not further disclose a method, wherein:
the pre-treatment feature representation and the post- treatment feature representation of the reference subject are captured
using functional magnetic resonance imaging (fMRI).
Ghosal teaches:
using functional magnetic resonance imaging (fMRI) (See Ghosal Abstract; system can use fMRI data.).
The system of Ghosal is applicable to the disclosure of Mastoridis as they both share characteristics and capabilities, namely, they are directed to using neural networks to analyze patient data using conditioning data. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Mastoridis to include multimodal data and classification techniques as taught by Ghosal. One of ordinary skill in the art before the effective filing date of the claimed invention would have been motivated to modify Mastoridis in order to achieve better classification accuracy than baseline methods, and generalize to a second dataset collected at a different site.
Lipsky teaches:
the pre-treatment feature representation and the post- treatment feature representation of the reference subject are captured (See Lipsky [0513] the system can use MRI imaging for confirm the efficacy of the course of treatment for treating the condition. It is understood that this means there is pre and post treatment MRI scans of the patient.).
The system of Lipsky is applicable to the disclosure of Mastoridis in view of Ghosal as they both share characteristics and capabilities, namely, they are directed to . It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Mastoridis to include proteomic, transcriptomic, and treatment outcome data as taught by Lipsky. One of ordinary skill in the art before the effective filing date of the claimed invention would have been motivated to modify Mastoridis in order to quickly and effectively identify genetic and phenotypic features (see Lipsky [0002]).
Regarding claim 10, Mastoridis in view of Ghosal and Lipsky discloses the method of claim 6 as discussed above. Mastoridis does not further disclose a method, wherein:
the pre-treatment feature representation and the post- treatment feature representation of the reference subject are captured using positron emission tomography (PET) imaging.
Lipsky teaches:
the pre-treatment feature representation and the post- treatment feature representation of the reference subject are captured using positron emission tomography (PET) imaging (See Lipsky [0513] the system can use PET imaging for confirm the efficacy of the course of treatment for treating the condition. It is understood that this means there is pre and post treatment PET scans of the patient.).
The system of Lipsky is applicable to the disclosure of Mastoridis in view of Ghosal as they both share characteristics and capabilities, namely, they are directed to . It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Mastoridis to include proteomic, transcriptomic, and treatment outcome data as taught by Lipsky. One of ordinary skill in the art before the effective filing date of the claimed invention would have been motivated to modify Mastoridis in order to quickly and effectively identify genetic and phenotypic features (see Lipsky [0002]).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Polykovskiy et al. (U.S. 2022/0310196) teaches a system and method for generating synthetic biological characteristic data for machine learning conditioning.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to BENJAMIN L HANKS whose telephone number is (571)270-5080. The examiner can normally be reached Monday-Friday 8am-5pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Shahid Merchant can be reached at (571) 270-1360. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/B.L.H./Examiner, Art Unit 3684
/Shahid Merchant/Supervisory Patent Examiner, Art Unit 3684
Prosecution Insights