DETAILED ACTION
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
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 1-14 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an
abstract idea without significantly more.
Step 1
Claims 1-14 are within the four statutory categories, however, as will be shown below, claims
1-14 are nonetheless unpatentable under 35 U.S.C. 101.
Claim 1 is representative of the inventive concept and recites:
A method for risk stratifying a patient for endometrial cancer using machine learning, comprising: accessing patient health data for a patient with a computer system;
accessing a machine learning model with the computer system, wherein the machine learning model has been trained on training data to generate classified feature data based on features present in a patients patient health data;
applying the patient health data to the machine learning model,
generating an output as classified feature data that indicate at least one of a risk stratification or classification of endometrial cancer in the patient based on features in their patient health data;
and outputting the classified feature data with the computer system.
Step 2A Prong One
The broadest reasonable interpretation of these steps includes mental processes because the
highlighted components can practically be performed by the human mind (in this case, the process of
applying and generating) or using pen and paper. Other than reciting generic computer components/functions such as “system”, “machine learning model”, and “computer system, nothing in the claims precludes the highlighted portions from practically being performed in the mind. For example, in claim 1, but for the generic computer language, the claim encompasses the user utilizing a model to input data and have the data output in a specific format. If a claim limitation, under its broadest reasonable interpretation, cover performance of the limitation in the mind but for the recitation of generic computer components/functions, then it falls within “Mental Processes” grouping of abstract ideas. Additionally, the mere nominal recitation of a generic computer does not take the claim limitation out of the mental process grouping. Thus, the claim recites a mental process.
Step 2A Prong Two
This judicial exception is no integrated into a practical application. In particular, the claims recite the
following additional limitations:
Claim 1 recites: “accessing patient health data for a patient with a computer system”, “accessing a machine learning model with the computer system, wherein the machine learning model has been trained on training data to generate classified feature data based on features present in a patients patient health data”, “generating an output as classified feature data that indicate at least one of a risk stratification or classification of endometrial cancer in the patient based on features in their patient health data”, “and outputting the classified feature data with the computer system”, “machine learning model”, and “computer system”
In particular, the additional elements do no integrate the abstract idea into a practical application, other
than the abstract idea per se, because the additional elements amount to no more than limitations
which:
Amount to mere instructions to apply an exception (MPEP 2106.05(f)). The limitations
are recited as being performed by a “machine learning model” and “computer system”. A computer is recited at a high level of generality and amounts to no more than mere instructions
to apply the exception using a generic computer. The model is used to generally apply the
abstract idea without limiting how the model functions. The model is described at a high level
such that it amounts to using a computer with a generic model to apply the abstract idea.
Add insignificant extra-solution activity (MPEP 2106.05(g)) to the abstract idea such as the
recitation of “accessing patient health data for a patient with a computer system”, “accessing a machine learning model with the computer system, wherein the machine learning model has been trained on training data to generate classified feature data based on features present in a patients patient health data”, “generating an output as classified feature data that indicate at least one of a risk stratification or classification of endometrial cancer in the patient based on features in their patient health data”, and “outputting the classified feature data with the computer system”.
Dependent claims 2, 4, 5 recites machine learning model
Dependent claim 2 recites artificial neural network
Dependent claim 3 recites artificial neural network, deep neural network
Dependent claim 4 recites inputting
Dependent claim 12 recites outputting
In particular, the additional elements do no integrate the abstract idea into a practical application, other
than the abstract idea per se, because the additional elements amount to no more than limitations
which:
Amount to mere instructions to apply an exception (MPEP 2106.05(f)). The limitations
are recited as being performed by a “machine learning model”, “artificial neural network”, and “deep neural network”. The model is used to generally apply the abstract idea without limiting how the model functions. The model is described at a high level such that it amounts to using a computer with a generic model to apply the abstract idea.
Add insignificant extra-solution activity (MPEP 2106.05(g)) to the abstract idea such as the
recitation of “inputting” and “outputting”.
Dependent claims 6-11 and 13-14 do not include any additional elements beyond those already
recited in independent claim 1 and dependent claims 2-5 and 12, hence do not integrate the aforementioned abstract idea into a practical 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 any other technology. Their collective function merely provides conventional computer implementation and do not impose a meaningful limit to integrate the abstract idea into a practical application.
Step 2B
Claim 1 does 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: A system in claim 1; amount to no
more than mere instructions to apply an exception to the abstract idea. Additionally, the additional
limitations, other than the abstract idea per se 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 demonstrated by the recitation of an additional element such as:
Accessing, which refers to retrieving, using, or interacting with data that is stored in various locations or formats (TLI Communications LLC v. AV Auto. LLC, 823 F.3d 607, 614, 118 USPQ2d 1744, 1748 (Fed. Cir. 2016)) in a manner that would be well-understood, routine, and conventional.
Inputting, which refers to the act of putting information into a computer or digital system (Para 0126, Wang(US-20230128064-A1) discloses: “The user input component 1134 can include such conventional input device technologies such as a keypad, keyboard, mouse, stylus pen, and/or touch screen, for example.”) in a manner that would be well-understood, routine, and conventional.
Outputting (Para 0100, Bjorkman(US 20220201342 A1) discloses: “Output device 170 may include one or more conventional mechanisms that output information to the user, including a display, a printer, one or more speakers, etc. “) in a manner that would be well-understood, routine, and conventional.
Dependent claims 6-11 and 13-14 do not include any additional elements beyond those already addressed above for independent claim 1 and dependent claims 2-5 and 12. Therefore, they are not deemed to be significantly more than the abstract idea because, as stated above, the limitations of the aforementioned dependent claims amount to no more than generally linking the abstract idea to a particular technological environment or field of use, and/or do not recite and additional elements not already recited in independent claim 1, hence does not amount to “significantly more” than the abstract idea. Thus, taken alone, the additional elements do not amount to significantly more than the abstract idea identified above. Furthermore, looking at the limitations as an ordered combination adds nothing that is not already present when looking at the elements taken individually, and there is no indication that the combination of elements improves the functioning of a computer or improves any other technology, and their collective function 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 1-11 are rejected under 35 U.S.C. 103 as being unpatentable over Cohen(US20180068083A1) in view of Hafez(US20220148736A1).
Claim 1
Cohen discloses:
A method for risk stratifying a patient for (Figure 1A, #10, Cohen discloses an EMR database accessible via a computer system); accessing a machine learning model with the computer system(Figure 11, #2010, Cohen discloses machine learning model accessed by a computer), wherein the machine learning model has been trained on training data to generate classified feature data based on features present in a patients patient health data; applying the patient health data to the machine learning model(Figure 11, Cohen discloses patient health data being applied to a machine learning model), generating an output as classified feature data that indicate at least one of a risk stratification(Para 0025, Cohen discloses an output of feature data with an output indicating likelihood of cancer based on patient data) or classification of (Para 0059, Cohen discloses computer-implemented machine learning, which inherently outputs via a computer system).
Cohen does not explicitly disclose: endometrial cancer
Hafez discloses:
endometrial cancer(Para 0331, Hafez discloses endometrial cancer)
Before the effective filing date of the claimed invention, it would have been obvious to one of
ordinary skill in the art to have modified the machine learning system for likelihood risk of cancer of Cohen, to add endometrial cancer, as taught by Hafez. One of ordinary skill would have been so motivated to provide a means to specify cancers such as endometrial cancer, in order to determine risk, to better improve patient outcomes, but in this case for predicting metastasis from patient records(Para 0008, Hafez discloses: “Extracting meaningful medical features from an ever-expanding quantity of health information tabulated for a similarly expanding cohort of patients having a multitude of sparsely populated features is a difficult endeavor.”).
Claim 2
Cohen discloses:
The method of claim 1, wherein the machine learning model comprises an artificial neural network(Para 0061, Cohen discloses artificial neural network).
Claim 3
Cohen discloses:
The method of claim 2, wherein the artificial neural network is a deep neural network(Para 0203, Cohen discloses deep learning neural network).
Claim 4
Cohen discloses:
The method of claim 1, further comprising selecting a subset of features from the patient health data and inputting only the subset of features to the machine learning model(Para 0318, Cohen discloses selecting parameters to be input into machine learning).
Claim 5
Cohen discloses:
The method of claim 4, wherein the subset of features is determined by training another machine learning model on patient health data collected from a cohort of patients(Para 0296, Cohen discloses training a model with patient cohort data).
Claim 6
Cohen discloses:
The method of claim 4, wherein the subset of features comprises patient demographic data(Para 0078, Cohen discloses demographics) and molecular data(Para 0372, Cohen discloses biomarker data).
Claim 7
Cohen discloses:
The method of claim 6, wherein the patient demographic data comprises age(Para 0371, Cohen discloses age) and race(Para 0440, Cohen discloses race).
Claim 8
Cohen discloses:
The method of claim 6, wherein the molecular data comprise at least one of TP53 status(Para 0146, Cohen discloses p53), mismatch repair (MMR) status(Para 0057, Hafez discloses MMR), fraction genome altered (FGA), and mutation counts.
Cohen does not explicitly disclose: mismatch repair (MMR) status
Hafez discloses:
mismatch repair (MMR) status(Para 0057, Hafez discloses MMR)
Before the effective filing date of the claimed invention, it would have been obvious to one of
ordinary skill in the art to have modified the machine learning system for likelihood risk of cancer of Cohen, to add mismatch repair status, as taught by Hafez. One of ordinary skill would have been so motivated to provide a means to specify genomic status of cancers in order to be improve treatment and patient outcomes, but in this case for predicting metastasis from patient records(Para 0008, Hafez discloses: “Extracting meaningful medical features from an ever-expanding quantity of health information tabulated for a similarly expanding cohort of patients having a multitude of sparsely populated features is a difficult endeavor.”).
Claim 9
Cohen discloses:
The method of claim 6, wherein the subset of features further comprises at least one of histologic subtype(Para 0374, Cohen discloses histologic subtype) or histologic grade.
Claim 10
Cohen discloses:
The method of claim 1, wherein the classified feature data comprise probability values(Figure 20, Cohen discloses probability value for developing cancer) for developing endometrial cancer.
Cohen does not explicitly disclose: endometrial cancer
Hafez discloses:
endometrial cancer(Para 0331, Hafez discloses endometrial cancer)
Before the effective filing date of the claimed invention, it would have been obvious to one of
ordinary skill in the art to have modified the machine learning system for likelihood risk of cancer of Cohen, to add endometrial cancer, as taught by Hafez. One of ordinary skill would have been so motivated to provide a means to specify cancers such as endometrial cancer, in order to determine risk, to better improve patient outcomes, but in this case for predicting metastasis from patient records(Para 0008, Hafez discloses: “Extracting meaningful medical features from an ever-expanding quantity of health information tabulated for a similarly expanding cohort of patients having a multitude of sparsely populated features is a difficult endeavor.”).
Claim 11
Cohen discloses:
The method of claim 1, wherein the classified feature data comprise category labels indicating low, moderate, or high risk(Para 0062, Cohen discloses low, medium, high for likelihood for developing cancer) for developing endometrial cancer.
Cohen does not explicitly disclose: endometrial cancer
Hafez discloses:
endometrial cancer(Para 0331, Hafez discloses endometrial cancer)
Before the effective filing date of the claimed invention, it would have been obvious to one of
ordinary skill in the art to have modified the machine learning system for likelihood risk of cancer of Cohen, to add endometrial cancer, as taught by Hafez. One of ordinary skill would have been so motivated to provide a means to specify cancers such as endometrial cancer, in order to determine risk, to better improve patient outcomes, but in this case for predicting metastasis from patient records(Para 0008, Hafez discloses: “Extracting meaningful medical features from an ever-expanding quantity of health information tabulated for a similarly expanding cohort of patients having a multitude of sparsely populated features is a difficult endeavor.”).
Claims 12-14 are rejected under 35 U.S.C. 103 as being unpatentable over Cohen(US20180068083A1) in view of Hafez(US20220148736A1) and in further view of Singh(US20190295726A1).
Claim 12
Cohen discloses:
The method of claim 1, wherein outputting the classified feature data comprises: analyzing the classified feature data with the computer system to determine a risk for the patient(Para 0378, Cohen discloses analyzing patient data to output a report of a patients likelihood of having cancer) developing (Para 0297, Cohen discloses a recommendation that high risk patients undergo more frequent screening);
Cohen does not explicitly disclose: endometrial cancer, outputting the order set to an electronic health record (EHR) of the patient using the computer system
Hafez discloses:
endometrial cancer(Para 0331, Hafez discloses endometrial cancer)
Before the effective filing date of the claimed invention, it would have been obvious to one of
ordinary skill in the art to have modified the machine learning system for likelihood risk of cancer of Cohen, to add endometrial cancer, as taught by Hafez. One of ordinary skill would have been so motivated to provide a means to specify cancers such as endometrial cancer, in order to determine risk, to better improve patient outcomes, but in this case for predicting metastasis from patient records(Para 0008, Hafez discloses: “Extracting meaningful medical features from an ever-expanding quantity of health information tabulated for a similarly expanding cohort of patients having a multitude of sparsely populated features is a difficult endeavor.”).
Hafez does not explicitly disclose: outputting the order set to an electronic health record (EHR) of the patient using the computer system
Singh discloses:
outputting the order set to an electronic health record (EHR) of the patient using the computer system(Para 0107, Singh discloses inputting data items into EMR of the subjects)
Before the effective filing date of the claimed invention, it would have been obvious to one of
ordinary skill in the art to have modified the machine learning system for likelihood risk of cancer of Cohen, to add outputting an order to an EMR system, as taught by Singh. One of ordinary skill would have been so motivated to provide a means to update a patient record with an order or prescription, the better enable physicians to understand patient history and improve treatment of a patient, but in this case for a system for monitoring subjects for hereditary cancers(Para 0008, Singh discloses: “ For example, genetic testing can cause anxiety and stress, genetic testing is expensive, and even favorable outcomes from genetic testing do not reduce the risk of cancer. Moreover, genetic testing raises privacy and discriminatory concerns, both from a socioeconomic and healthcare/insurance perspectives. This, in turn, can lead to additional anxiety and stress. Accordingly, it is not feasible or desirable to genetically screen every person for increased cancer risks.”).
Claim 13
Cohen discloses:
The method of claim 12, wherein the determined risk for the patient developing (Para 0297, Cohen discloses a recommendation that high risk patients undergo more frequent screening) to determine an extent of nodal involvement for endometrial cancer in the patient.
Cohen does not explicitly disclose: endometrial cancer, risk of nodal involvement
Hafez discloses:
endometrial cancer(Para 0331, Hafez discloses endometrial cancer)
risk of nodal involvement(Para 0446, Hafez discloses risk of metastasis to tissues including lymph nodes)
Before the effective filing date of the claimed invention, it would have been obvious to one of
ordinary skill in the art to have modified the machine learning system for likelihood risk of cancer of Cohen, to add endometrial cancer and risk of nodal involvement, as taught by Hafez. One of ordinary skill would have been so motivated to provide a means to specify cancers such as endometrial cancer and determine metastasis to lymph nodes, in order to determine risk, to better improve patient outcomes, but in this case for predicting metastasis from patient records(Para 0008, Hafez discloses: “Extracting meaningful medical features from an ever-expanding quantity of health information tabulated for a similarly expanding cohort of patients having a multitude of sparsely populated features is a difficult endeavor.”).
Claim 14
Cohen discloses:
The method of claim 12, wherein the order set indicates a treatment option(Para 0270, Cohen discloses, treatment option generation if patient is diagnosed with cancer) for the patient based on the determined risk for the patient developing
Cohen does not explicitly disclose: endometrial cancer
Hafez discloses:
endometrial cancer(Para 0331, Hafez discloses endometrial cancer)
Before the effective filing date of the claimed invention, it would have been obvious to one of
ordinary skill in the art to have modified the machine learning system for likelihood risk of cancer of Cohen, to add endometrial cancer, as taught by Hafez. One of ordinary skill would have been so motivated to provide a means to specify cancers such as endometrial cancer, in order to determine risk, to better improve patient outcomes, but in this case for predicting metastasis from patient records(Para 0008, Hafez discloses: “Extracting meaningful medical features from an ever-expanding quantity of health information tabulated for a similarly expanding cohort of patients having a multitude of sparsely populated features is a difficult endeavor.”).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Saria(US20120290319A1) discloses a system which codes patient outcomes based on EMR data.
Smyth(US20200239968A1) discloses a prognostic and treatment response predictive method.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SHERYL GOPAL PATEL whose telephone number is (703)756-1990. The examiner can normally be reached Monday - Friday 5:30am to 2:30pm PST.
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, Kambiz Abdi can be reached at 571-272-6702. 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.
/S.G.P./Examiner, Art Unit 3685
/KAMBIZ ABDI/Supervisory Patent Examiner, Art Unit 3685