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 .
This listing of claims will replace all prior versions, and listings of claims in the application.
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 2-5, 7-22 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Step 1: claims 2-5, 7-22 are directed to either a process, machine, manufacture or composition of matter.
With respect to claim 1:
2A Prong 1:
predict an increased risk of having or developing cancer, for patient (using AI to predict amounts to a mental process in the same way that a human can predict the weather with or without a computer);
assigning a risk score of having or developing cancer to the patient to produce an assigned risk score (mental process – user can manually perform raw thinking in their head as a first stage and then using paper and pen to perform mathematical operation);
when an output of the first classifier model is a numerical expression of the percent likelihood of having or developing cancer (further define mental process numerical expressions and percentages can be obtained by mental process – user can manually perform raw thinking in their head as a first stage and then using paper and pen to perform mathematical operation);
classifying the patient into a patient risk category of having or developing cancer using the assigned risk score, wherein an assigned risk score having a percent likelihood of having or developing cancer greater than a percent prevalence of cancer in the population is deemed an increased risk category (Abstract idea of analyzing data. Mental process. A human- mind with pen and paper can generate/determine data; can be obtained by mental process – user can manually perform raw thinking in their head as a first stage and then using paper and pen to perform mathematical operation);
detecting (encompasses mental observations or evaluations, e.g., a computer programmer’s mental identification of data);
2A Prong 2: This judicial exception is not integrated into a practical application.
Additional elements:
computer-implemented system comprising at least one processor and at least one memory (computer component is recited at a high level of generality and amounts to no more than mere instructions to apply the exception using a generic computer component; the mere recitation of a generic computer cannot transform a patent-ineligible abstract idea into a patent-eligible invention." Alice, 134 S. Ct. at 2358);
classifier models (Adding the words “apply it” (or an equivalent) with the judicial exception, or mere 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));
obtaining age, gender and measured values of one or more biomarker features of a panel of pan and/or specific tumor biomarkers in a sample from the patient (mere data gathering and output recited at a high level of generality - insignificant extra-solution activity to the judicial exception - see MPEP 2106.05(g));
a first classifier model using input variables of age, gender and measured values of the panel of pan and/or specific tumor biomarkers, wherein each measured value has a value of zero or one(Adding the words “apply it” (or an equivalent) with the judicial exception, or mere 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));
a diagnostic indicator, for a population of patients(computer component is recited at a high level of generality and amounts to no more than mere instructions to apply the exception using a generic computer component; the mere recitation of a generic computer cannot transform a patent-ineligible abstract idea into a patent-eligible invention." Alice, 134 S. Ct. at 2358);
the first classifier model(Adding the words “apply it” (or an equivalent) with the judicial exception, or mere 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))
machine learning system(Adding the words “apply it” (or an equivalent) with the judicial exception, or mere 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));
using training data that comprises values of age, gender and biomarker features selected from a panel of pan and/or specific tumor biomarkers, and an input for each biomarker feature used to train the first classifier model has a measured value or is absent (Adding the words “apply it” (or an equivalent) with the judicial exception, or mere 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) – Examiner’s note: high level recitation of training a machine learning model with previously determined data);
providing notification to a user of the patient risk category and/or assigned risk score (mere data gathering and output recited at a high level of generality - insignificant extra-solution activity to the judicial exception - see MPEP 2106.05(g)).
2B: The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
Additional elements:
computer-implemented system comprising at least one processor and at least one memory (computer component is recited at a high level of generality and amounts to no more than mere instructions to apply the exception using a generic computer component; the mere recitation of a generic computer cannot transform a patent-ineligible abstract idea into a patent-eligible invention." Alice, 134 S. Ct. at 2358);
classifier models (Adding the words “apply it” (or an equivalent) with the judicial exception, or mere 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));
obtaining age, gender and measured values of one or more biomarker features of a panel of pan and/or specific tumor biomarkers in a sample from the patient (mere data gathering and output recited at a high level of generality - insignificant extra-solution activity to the judicial exception - see MPEP 2106.05(g));
a first classifier model using input variables of age, gender and measured values of the panel of pan and/or specific tumor biomarkers, wherein each measured value has a value of zero or one(Adding the words “apply it” (or an equivalent) with the judicial exception, or mere 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));
a diagnostic indicator, for a population of patients(computer component is recited at a high level of generality and amounts to no more than mere instructions to apply the exception using a generic computer component; the mere recitation of a generic computer cannot transform a patent-ineligible abstract idea into a patent-eligible invention." Alice, 134 S. Ct. at 2358);
the first classifier model(Adding the words “apply it” (or an equivalent) with the judicial exception, or mere 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))
machine learning system(Adding the words “apply it” (or an equivalent) with the judicial exception, or mere 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));
using training data that comprises values of age, gender and biomarker features selected from a panel of pan and/or specific tumor biomarkers, and an input for each biomarker feature used to train the first classifier model has a measured value or is absent (Adding the words “apply it” (or an equivalent) with the judicial exception, or mere 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) – Examiner’s note: high level recitation of training a machine learning model with previously determined data);
providing notification to a user of the patient risk category and/or assigned risk score (mere data gathering and output recited at a high level of generality - insignificant extra-solution activity to the judicial exception - see MPEP 2106.05(g));
Further, the obtaining/notifying steps were considered to be extra-solution activity in Step 2A Prong 2, and thus it is re-evaluated in Step 2B to determine if it is more than what is well-understood, routine, conventional activity in the field. The receiving and/or transmitting limitations constitute extra-solution activity. See buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355 (Fed. Cir. 2014) ("That a computer receives and sends the information over a network-with no further specification-is not even arguably inventive."). The court decisions cited in MPEP 2106.05(d)(II) indicate that merely Receiving and/or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information). Thereby, a conclusion that the claimed receiving/transmitting steps are well-understood, routine, conventional activity is supported under Berkheimer. The claim is not patent eligible.
3. (Currently Amended) The method of claim 2, wherein the first training data comprises values from a panel of at least two, three, or four biomarkers (further define mental process, user can model data and/or perform math).
4. (Original) The method of claim 3, wherein the panel of biomarkers is selected from AFP, CEA, CA125, CA19-9, CA 15-3, CYFRA21-1, PSA and SCC(further define mental process, user can model data and/or perform math).
5. (Original) The method of claim 4, wherein the panel of biomarkers includes AFP, CEA, CA19-9, and PSA; AFP, CEA and PSA; or AFP and CEA (further define mental process, user can model data and/or perform math).
7. (Currently Amended) The method of claim 1,wherein the first classifier model has an improved performance of a Receiver Operator Characteristic (ROC) curve having a sensitivity value of at least 0.85 and a specificity value of at least 0.8(further define mental process, user can model data and/or perform math).
8. (Currently Amended) The method of claim 1,wherein the risk category comprises low risk, moderate risk or high risk (further define mental process, user can model data and/or perform math using thresholds).
9. (Currently Amended) The method of claim 8, wherein the increased risk category comprises moderate risk or high risk(further define mental process, user can model data and/or perform math using thresholds).
10. (Currently Amended) The method of claim 1,wherein the diagnostic testing is radiographic screening or a tissue biopsy (data gathering, further define mental process, user can model data and/or perform math).
11. (Currently Amended) The method of claim 1,further comprising:(1) obtaining one or more test results from the diagnostic testing which confirm or deny the presence of cancer in the patient (data gathering); (2) incorporating the one or more test results into the first training data for further training of the first classifier model of the machine learning system(or an equivalent) with the judicial exception, or mere 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) – Examiner’s note: high level recitation of training a machine learning model with previously determined data); and (3) generating an improved first classifier model by the machine learning system(further define mental process, user can model data and/or perform math).
12. (Currently Amended) The method of claim 1 wherein the first classifier model comprises a support vector machine, a decision tree, a random forest, a neural network, a deep learning neural network, or a logistic regression algorithm (additional element considered to be generally linking the use of the judicial exception to a particular technological environment or field of use – see MPEP 2106.05(h)).
13. (Currently Amended) The method of claim 1 wherein the cancer is selected (data gathering) from the group consisting of: breast cancer, bile duct cancer, bone cancer, cervical cancer, colon cancer, colorectal cancer, gallbladder cancer, kidney cancer, liver or hepatocellular cancer, lobular carcinoma, lung cancer, melanoma, ovarian cancer, pancreatic cancer, prostate cancer, skin cancer, and testicular cancer(further define mental process, user can model data and/or perform math).
14. (Currently Amended) The method of claim 1 wherein the first training data comprises a group of data from a group of patients with no cancer diagnosis three or more months after providing a sample(further define mental process, user can model data and/or perform math).
15. (Currently Amended) The method of claim 1 wherein the first training data comprises a group of data from a group of patients with a cancer diagnosis three or more months after providing a sample(further define mental process, user can model data and/or perform math).
16. (Currently Amended) The method of claim 1 wherein the threshold is a probability value of 0.5(further define mental process, user can model data and/or perform math).
17. (Currently Amended) The method of claim 1 wherein the first training data comprises a greater number of patients without cancer than with cancer, and further comprising reprocessing the first training data by using a stratified sampling technique to improve selection of negative samples(further define mental process, user can model data and/or perform math).
18. (Currently Amended) The method of claim 1 wherein patients classified into the increased risk category by the first classifier model are further classified using a second classifier model, wherein the second classifier model is generated by the machine learning system using second training data that comprises values of a panel of at least two biomarkers and a diagnostic indicator from a population of patients, wherein the second classifier model predicts at least one most likely organ system malignancy for that patient by assigning a class membership corresponding to the most likely organ system malignancy, using input variables of the measured values of the panel of biomarkers from the patient (further define mental process, user can model data and/or perform math; classifying/clustering is a form of math).
19. (Original) The method of claim 18, wherein training data further comprises values of age from the population of patients(further define mental process, user can model data and/or perform math).
20. (Currently Amended) The method of claim 19, wherein the input variables further comprise age(further define mental process, user can model data and/or perform math).
21. (Currently Amended) The method of claim 1 that comprises providing a notification (transmitting) to a user for diagnostic testing of the patient when the patient is predicted to have the organ system-based malignancy(further define mental process, user can model data and/or perform math).
22. (Currently Amended) The method of claim 1 wherein the patient is asymptomatic(further define mental process, user can model data and/or perform math).
Response to Arguments
It is well-settled that collecting and analyzing information by steps people go through in their minds or by mathematical algorithms, without more, are mental processes in the abstract-idea category. Elec. Power Grp., LLC v. Alstom S.A., 830 F.3d 1350, 1353-54 (Fed. Cir. 2016); see SAP Am., Inc. v. InvestPic, LLC, 898 F.3d 1161, 1167 (Fed. Cir. 2018) ("[S]electing certain information, analyzing it using mathematical techniques, and reporting or displaying the results of the analysis" is abstract); Intellectual Ventures I LLC v. Cap. One Fin. Corp., 850 F.3d 1332, 1341 (Fed. Cir. 2017) ("Organizing, displaying, and manipulating data of particular documents" is abstract.); FairWarning IP, LLC v. Iatric Sys., Inc., 839 F.3d 1089, 1096-97 (Fed. Cir. 2016) (compiling and combining disparate data sources to generate a full picture of a user's activity, identity, frequency of activity, and the like in a computer environment to detect potential fraud does not differentiate a process from ordinary mental processes); In re Killian, 45 F.4th 1373, 1379 (Fed. Cir. 2022) ("These steps can be performed by a human, using 'observation, evaluation, judgment, [and] opinion,' because they involve making determinations and identifications, which are mental tasks humans routinely do").
The claims amount to data analysis/manipulation and using some form of AI as a tool. The transformation of data, or the mere "manipulation of basic mathematical constructs [i.e.,] the paradigmatic 'abstract idea,"' is not a transformation sufficient to integrate a judicial exception into a practical application. CyberSource v. Retail Decisions, 654 F.3d 1366, 1372 n.2 (Fed. Cir. 2011) (quoting In re Warmerdam, 33 F.3d 1354, 1355, 1360 (Fed. Cir. 1994)).
Claiming AI on a high level can amount to using a black box without specifying any real details of how the AI operates or what’s in the black box. The claims need to specify the technical details of the AI.
Although the claims may specify an improvement they are only improving the abstract idea not a computer.
Training a model/classifier to learn amounts to adding the words “apply it” (or an equivalent) with the judicial exception, or mere 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).
Using a trained machine learning model to e.g., classify… amounts to adding the words “apply it” (or an equivalent) with the judicial exception, or mere 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).
Using AI to predict amounts to a mental process in the same way that a human can predict the weather with or without a computer.
"The courts consider a mental process (thinking) that "can be performed in the human mind, or by a human using a pen and paper" to be an abstract idea." MPEP § 2106.04(a)(2).III. "Accordingly, the "mental processes" abstract idea grouping is defined as concepts performed in the human mind, and examples of mental processes include observations, evaluations, judgments, and opinions." Id. For the purposes of this abstract idea, "[t]he courts do not distinguish between mental processes that are performed entirely in the human mind and mental processes that require a human to use a physical aid (e.g., pen and paper or a slide rule) to perform the claim limitation."
If the application claims the inventive concept (from the disclosure) and the claims are drawn to the specifics of e.g., learning or training, such as the how and for what purpose the training occurs, the claims may be eligible/statutory. If the generic computer or processor is merely "used for", "applied to" or "using" an AI learning/training algorithm, process or equivalent without claimed details, it will most often fall into the "Mere Instructions to Apply an Exception" as set forth in MPEP 2106.05(f). When a claim merely recites only the idea of a solution or outcome, i.e. the claim fails to recite details of how a solution to a problem is accomplished, as described in 2106.05(f)(1), it is rejected as ineligible. Also, use of an existing AI or learning technique or method, set forth to be WURC (in accordance with MPEP 2106.05(d)), may also prove to be ineligible.
If the claims are merely "using" existing "artificial intelligence techniques" then learning/training/AI is not the inventive concept but is merely a tool used to manipulate data. This can be a process that was previously performed by "human agents" and may now be automated. Learning, training, "updating" and/or "dynamically modifying" are insignificant computer activities, shown to be WURC in accordance with MPEP 2106.05(d)(II)(iii), for instance.
Claims do not specify a clear practical application. It is true that making physical changes to at least a portion of hardware is not a mental process but if applicant merely states e.g., “making physical changes” without any more description it would be so broad that it would be directed to insignificant extra-solution activity. If the physical changes were more specifically laid out, examiner may agree that the physical changes make a claim eligible but if the examiner cannot easily identify what physical changes are positively made the claimed physical changes amount to mere extra-solution activity.
In order for an abstract idea to be integrated into a practical application, the improvement in a given technical field must be a byproduct of the additional elements. An inventive concept "cannot be furnished by the unpatentable law of nature (or natural phenomenon or abstract idea) itself”, as stated in MPEP 2106.5 (1). Applicant should state where within the claim limitations such an improvement is made.
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.
Claim(s) 2-5, 7-22 is/are rejected under 35 U.S.C. 103 as being unpatentable over Kearney (US 2018/0067119) combined with Drake (WO 2019200410) and JP 2016538884.
Kearney discloses
2. (Currently Amended) A computer-implemented method configured to use a previously generated classifier, trained with a machine learning system (models comprise of classifiers and are trained and retrained to reach optimization over iterations, see e.g., “logistic regression classifier trained on all small samples”, 0201), for use to identify an asymptomatic patient likely to have cancer (“In many asymptomatic patients, radiological screens such as computed tomography (CT) scanning are a first step in the diagnostic paradigm. Pulmonary nodules (PNs) or indeterminate nodules are located in the lung and are often discovered during screening of both high risk patients or incidentally.”, 0003), comprising:
a) obtaining input variables (e.g., various forms of blood tests, scanning or imaging, “computed tomography (CT) scanning are a first step in the diagnostic paradigm”, “current medical practice dictates scans every three to six months for at least two years to monitor for lung cancer”, 0003) from the patient for the classifier of age, gender and measured values of one or more biomarker features of a panel of pan and/or specific tumor biomarkers in a sample from the patient (many types of profile data and test data e.g., scans/imaging data can be used as input or training data, see e.g., “careful matching of cancer and benign cohorts on age, gender, nodule size and clinical site was critical in not only avoiding bias, but in the discovery and validation of a classifier that provides a score independent of these clinical factors as well as smoking history.”, 0387; “A two-class classifier is an algorithm that uses data points from measurements from a sample and classifies the data into one of two groups”, 0062), wherein each measured value has a value of zero or one (not further defined, reads on a probability or likelihood of a measured value from a scan/test having a probability of 0 or 1, 0016; reads on 0.0, 0.1, 1.0, 0.2 etc., 0151, example 2, 0238, 0082-0083; “The term “score” or “scoring” refers to the refers to calculating a probability likelihood for a sample. For the present invention, values closer to 1.0 are used to represent the likelihood that a sample is cancer, values closer to 0.0 represent the likelihood that a sample is benign”, 0056);
using the classifier with the selected input variables, wherein the classifier generates an assigned risk score of having or developing cancer for the patient to produce an assigned risk score (reads on scores, likelihood, probability, “the determining the likelihood of cancer is determined by the sensitivity, specificity, negative predictive value or positive predictive value associated with the score”, 0019),
wherein:
when an output of the first classifier model (model can comprise of a classifier; classifier can be referred to as a model) is a numerical expression of the percent likelihood of having or developing cancer (0151, example 2, 0238, 0082-0083), and wherein the first classifier model (reads on initial or untrained model/classifier before retraining) is generated by a machine learning system using training data that comprises values of age, gender and biomarker features selected from a panel of pan and/or specific tumor biomarkers, and an input for each biomarker feature used to train the first classifier model has a measured value or is absent (“careful matching of cancer and benign cohorts on age, gender, nodule size and clinical site was critical in not only avoiding bias, but in the discovery and validation of a classifier that provides a score independent of these clinical factors as well as smoking history.”, 0387; “A two-class classifier is an algorithm that uses data points from measurements from a sample and classifies the data into one of two groups”, 0062; “The term “incremental information” refers to information that may be used with other diagnostic information to enhance diagnostic accuracy. Incremental information is independent of clinical factors such as including nodule size, age, or gender”, 0055); and,
c) classifying (“biomarker proteins and methods of using these biomarker proteins or panels thereof to diagnose, classify, and monitor various lung conditions. The methods and compositions provided herein may be used to diagnose or classify a subject as having lung cancer or a non-cancerous condition, and to distinguish between different types of cancer (e.g., malignant versus benign, SCLC versus NSCLC)”, abstract; “diagnose, classify and monitor lung conditions, and particularly lung cancer. The present invention uses a blood-based multiplexed assay to distinguish benign pulmonary nodules from malignant pulmonary nodules to classify patients with or without lung cancer”, 0008, 0061-4) the patient into a patient risk category of having or developing cancer using the assigned risk score, wherein an assigned risk score having a percent likelihood of having or developing cancer greater than a percent prevalence of cancer in the population is deemed an increased risk category (e.g., “determining the likelihood that a lung condition in a subject is cancer by measuring an abundance of a panel of proteins in a sample obtained from the subject; calculating a probability of cancer score based on the protein measurements and ruling out cancer for the subject if the score is lower than a pre-determined score”, 0006; “calculating a probability of cancer score based on the protein measurements and ruling in the likelihood of cancer for the subject if the score is higher than a pre-determined score.”, 0007; “subject is at risk of developing lung cancer”, 0008; 0061-4); and,
d) providing notification to a user of the patient risk category and/or assigned risk score (see below).
Kearney fails to particularly call for the classifier to be a model or trained by a ML model and/or classifier model is generated by a machine learning system using training data and providing notification to a user of the patient risk category and/or assigned risk score.
Drake more clearly teaches classifier model is generated by a machine learning system using training data (comes down to semantics, a classifier can be referred to as a model, “machine learning model to train a classifier for medical diagnostic”, 0103-0104; “machine learning model comprising the classifier, the machine learning model trained using training vectors obtained from training biological samples”, 0010; using features also, “measure sets of values representative of classes of molecules, identify sets of features and feature vectors from assay data, process feature vectors using a machine learning model to obtain output classifications, and train a machine learning model (e.g., iteratively search for optimal values of parameters of the machine learning model).”, 0216-0219).
It would have been obvious to combine the references before the effective filing date because they are in the same field of endeavor and it is well-known for classifiers to be referred to as models. Training classifiers on various forms of input data in order to determine a probability/risk score allows for patient data to be combined or analyzed so they know the likelihood of the disease.
JP 2016538884 teaches informing the patients of outcomes (“The term “diagnostic threshold” refers to a threshold at which a patient can be informed of the presence of certain symptoms (e.g., bladder cancer).”; “Contact with a patient scheduled for informed consent cystoscopy to discuss possible participation. Provide patients with information on the nature of the study and obtain consent. Patients will provide information regarding demographics, occupations and smoking history, and ensure that they fully understand the information and form of consent prior to the provision of their urine samples.”).
It would have been obvious to combine the references before the effective filing date because they are in the same field of endeavor and it is well-known to receive patient consent before collecting labs or samples and to inform patients of their outcomes so they can plan for a therapy.
3. (Previously Presented) The method of claim 2, wherein the first training data comprises values from a panel of at least two, three, or four biomarkers (scans, images, various test data, “using these biomarker proteins or panels thereof to diagnose, classify, and monitor various lung conditions”, abstract, 0003, 0006, 0101).
4. (Original) The method of claim 3, wherein the panel of biomarkers is selected from AFP, CEA, CA125, CA19-9, CA 15-3, CYFRA21-1, PSA and SCC(0303, 0423, also see Drake: 0116, 0201, 0209, 0338, 0421, 0430).
5. (Original) The method of claim 4, wherein the panel of biomarkers includes AFP, CEA, CA19-9, and PSA; AFP, CEA and PSA; or AFP and CEA(0303, 0423, also see Drake: 0116, 0201, 0209, 0338, 0421, 0430).
6. (Canceled).
7. (Previously Presented) The method of claim 1, wherein the first classifier model has an improved performance of a Receiver Operator Characteristic (ROC) curve having a sensitivity value of at least 0.85 and a specificity value of at least 0.8(0054, 0063, 0110-0111, 0150-2, 0204).
8. (Previously Presented) The method of claim 1, wherein the risk category comprises low risk, moderate risk or high risk (relative terms, subjective, not further defined, reads on levels of scores, probability, etc. 0003, 0006-9,0056).
9. (Previously Presented) The method of claim 8, wherein the increased risk category comprises moderate risk or high risk(relative terms, subjective, not further defined, reads on levels of scores, probability, etc. 0003, 0006-9,0056).
10. (Previously Presented) The method of claim 1, wherein the diagnostic testing is radiographic screening or a tissue biopsy(scans, images, biopsy, nodules, various test data, “using these biomarker proteins or panels thereof to diagnose, classify, and monitor various lung conditions”, abstract, 0003, 0006, 0101).
11. (Previously Presented) The method of claim 1, further comprising:(1) obtaining one or more test results from the diagnostic testing which confirm or deny the presence of cancer in the patient(scans, images, biopsy, nodules, various test data, “using these biomarker proteins or panels thereof to diagnose, classify, and monitor various lung conditions”, abstract, 0003, 0006, 0101);(2) incorporating the one or more test results into the first training data for further training of the first classifier model of the machine learning system (0028, 0276, 0407, 0416); and(3) generating an improved first classifier model by the machine learning system (classifiers/models are trained and retrained).
12. (Previously Presented) The method of claim 1 wherein the first classifier model comprises a support vector machine, a decision tree, a random forest, a neural network, a deep learning neural network, or a logistic regression algorithm(well-known AI algorithms, not the point of novelty, regression, 0016, 0059, 0121, 0198, 0268-9; also see Drake: 00020).
13. (Previously Presented) The method of claim 1 wherein the cancer is selected from the group consisting of: breast cancer, bile duct cancer, bone cancer, cervical cancer, colon cancer, colorectal cancer, gallbladder cancer, kidney cancer, liver or hepatocellular cancer, lobular carcinoma, lung cancer, melanoma, ovarian cancer, pancreatic cancer, prostate cancer, skin cancer, and testicular cancer (“The methods and compositions provided herein may be used to diagnose or classify a subject as having lung cancer or a non-cancerous condition, and to distinguish between different types of cancer (e.g., malignant versus benign, SCLC versus NSCLC).”, abstract; also see Drake: 0002-0003; 0021).
14. (Previously Presented) The method of claim 1 wherein the first training data comprises a group of data from a group of patients with no cancer diagnosis three or more months after providing a sample(reads on using training data from healthy or at risk patients, its inherent, diagnosing cancer before, during and after remission, 0433; “calculating a probability of cancer score based on the protein measurements and ruling out cancer for the subject if the score is lower than a pre-determined score”, 0006; “For patients considered low risk for malignant nodules, current medical practice dictates scans every three to six months for at least two years to monitor for lung cancer. The time period between identification of a PN and diagnosis is a time of medical surveillance or “watchful waiting” and may induce stress on the patient and lead to significant risk and expense due to repeated imaging studies.”, 0003).
15. (Previously Presented) The method of claim 1 wherein the first training data comprises a group of data from a group of patients with a cancer diagnosis three or more months after providing a sample(reads on using training data from healthy or at risk patients, its inherent, diagnosing cancer before, during and after remission, 0433; “calculating a probability of cancer score based on the protein measurements and ruling out cancer for the subject if the score is lower than a pre-determined score”, 0006; “For patients considered low risk for malignant nodules, current medical practice dictates scans every three to six months for at least two years to monitor for lung cancer. The time period between identification of a PN and diagnosis is a time of medical surveillance or “watchful waiting” and may induce stress on the patient and lead to significant risk and expense due to repeated imaging studies.”, 0003).
16. (Previously Presented) The method of claim 1 wherein the threshold is a probability value of 0.5(design choice, reads on a probability or likelihood of a measured value from a scan/test having a probability of 0-1, 0016; reads on 0.0, 0.1, 1.0, 0.2 etc., 0151, example 2, 0238, 0082-0083; “The term “score” or “scoring” refers to the refers to calculating a probability likelihood for a sample. For the present invention, values closer to 1.0 are used to represent the likelihood that a sample is cancer, values closer to 0.0 represent the likelihood that a sample is benign”, 0056).
17. (Previously Presented) The method of claim 1 wherein the first training data comprises a greater number of patients without cancer than with cancer, and further comprising reprocessing the first training data by using a stratified sampling technique to improve selection of negative samples.
Kearney fails to particularly call for stratified sampling technique.
Drake teaches stratified sampling technique (“a population may be stratified into responders and non- responders include but are not limited to: chemotherapeutic agents including sorafenb,”, 0317-0319, 0476).
It would have been obvious to combine the references before the effective filing date because they are in the same field of endeavor and it is well-known to choose to use a stratified sampling technique because it merely amounts to a probability sampling technique where researchers divide a total population into homogeneous, non-overlapping subgroups (strata) based on shared characteristics like age, income, or gender.
18. (Previously Presented) The method of claim 1 wherein patients classified into the increased risk category by the first classifier model are further classified using a second classifier model (does not say when this happens, reads on using a model that is retrained or a model months later), wherein the second classifier model is generated by the machine learning system using second training data that comprises values of a panel of at least two biomarkers and a diagnostic indicator from a population of patients, wherein the second classifier model predicts at least one most likely organ system malignancy for that patient by assigning a class membership corresponding to the most likely organ system malignancy, using input variables of the measured values of the panel of biomarkers from the patient (“Examples of biological samples include tissue, organs, or bodily fluids such as whole blood, plasma, serum, tissue, lavage or any other specimen used for detection of disease”, 0075).
19. (Original) The method of claim 18, wherein training data further comprises values of age from the population of patients (“Lung cancer risk according to the “National Lung Screening Trial” is classified by age”, 0095, Tables 7-8, 0142; 0055).
20. (Previously Presented) The method of claim 19, wherein the input variables further comprise age (same limitation repeated several times, see claim 1, “Lung cancer risk according to the “National Lung Screening Trial” is classified by age”, 0095, Tables 7-8, 0142; 0055).
21. (Previously Presented) The method of claim 1 that comprises providing a notification to a user for diagnostic testing of the patient when the patient is predicted (see above probabilities, likelihoods) to have the organ system- based malignancy
JP 2016538884 teaches informing the patients of outcomes (“The term “diagnostic threshold” refers to a threshold at which a patient can be informed of the presence of certain symptoms (e.g., bladder cancer).”; “Contact with a patient scheduled for informed consent cystoscopy to discuss possible participation. Provide patients with information on the nature of the study and obtain consent. Patients will provide information regarding demographics, occupations and smoking history, and ensure that they fully understand the information and form of consent prior to the provision of their urine samples.”).
It would have been obvious to combine the references before the effective filing date because they are in the same field of endeavor and it is well-known to receive patient consent before collecting labs or samples and to inform patients of their outcomes so they can plan for a therapy.
22. (Previously Presented) The method of claim 1 wherein the patient is asymptomatic (“asymptomatic patients, radiological screens such as computed tomography (CT) scanning are a first step in the diagnostic paradigm.”, 0003; Drake: 0240).
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Becich (US 2023/0266342) teaches measured value has a value of zero or one (see e.g., “measured value has a value of zero or one”, 0131-0133) predicting disease using varying risk levels and models (0145).
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to DAVID R VINCENT whose telephone number is (571)272-3080. The examiner can normally be reached ~Mon-Fri 12-8:30.
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, Alexey Shmatov can be reached at 5712703428. 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.
/DAVID R VINCENT/Primary Examiner, Art Unit 2123
Prosecution Insights