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 .
Notice to Applicant
This communication is in response to the amendment filed 4/21/2026. Claims 76, 79, 83, 89, 91, 94, 98, and 104-106 have been amended. Claims 78 and 93 have been canceled. Claims 107 and 108 have been added. Claims 76, 77, 79-92, and 94-108 are currently pending and have been examined.
Response to Arguments
A. Applicant's arguments with respect to the rejection under 35 USC 101 have been fully considered but they are not persuasive.
Applicant argues on page 10 of the response that claims 76, 91, and 106 are patent eligible “for at least the reason that they encompass administering a particular treatment-namely one or more biochemical interventions-that treat a particular disease: cancer.” Examiner respectfully disagrees.
Examiner initially notes that claims 76 and 106 do not recite a step of administering a treatment as argued by Applicant. Applicant’s arguments therefore do not reflect the actual scope and language of claims 76 and 106.
With respect to claim 91, the specific considerations for whether a claim integrates a recited abstract idea into a practical application by effecting a particular treatment or prophylaxis for a disease or medical condition are:
a) the particularity or generality of the treatment or prophylaxis;
b) whether the limitations have more than a nominal or insignificant relationship to the exception; and
c) whether the limitations are merely extra-solution activity or a field of use.
Initially, the treatment or prophylaxis must be “particular,” i.e. specifically identified. MPEP 2106.04(d)(2) provides the example of a claim reciting mentally analyzing information to identify if a patient has a genotype associated with poor metabolism of beta blocker medications, wherein the additional element of “administering a lower than normal dosage of a beta blocker medication to a patient identified as having the poor metabolizer genotype” was considered to be “particular.” Conversely, MPEP 2106.04(d)(2) states that the recitation of “administering a suitable medication to a patient” would not constitute a “particular” treatment or prophylaxis in conjunction with the same abstract idea.
In addition to falling within the scope of the abstract idea itself, the cited limitation in claim 91 only recites administering “a selected subset of the one or more biochemical interventions,” which does not constitute a particular treatment or prophylaxis. The general recitation of administering selected biochemical interventions to treat a cancer is not sufficient to integrate the abstract idea into a practical application or to amount to significantly more than the abstract idea.
The rejection under 35 USC 101 is maintained.
B. Applicant’s arguments with respect to the rejection under 35 USC 103 have been considered but are unpersuasive in part and moot in part as set out below.
Applicant argues starting on page 11 that Lipsky does not teach the combination of elements (ii)-(iv) of claim 76. Examiner maintains that Lipsky teaches particular ones of the emphasized limitations, including determining probabilistic predictions of clinical outcomes of a set of treatment options for a disease or disorder based at least in part on clinical data of test subjects wherein the clinical outcomes comprise future uncertainty (see e.g. [114], [115], [170], [171], [470], and [481]. Examiner directs Applicant to full citations provided below), and applying the prediction module to at least the clinical data of the subject to determine probabilistic predictions of clinical outcomes in response to the one or more biochemical interventions (see e.g. paragraphs 452, 477, 480, 487, 488, and 607. Examiner directs Applicant to full citations provided below). Applicant does not provide specific arguments addressing why the cited Lipsky reference does not teach the argued limitations.
Applicant’s arguments regarding the limitations including determining, by the trained machine learning model, a plurality of treatment features for the one or more biochemical interventions, wherein the plurality of treatment features comprise a chemical structure and a biological target of the one or more biochemical interventions and applying the prediction module to at least the clinical data of the subject and the plurality of treatment features of the one or more biochemical interventions are moot because no previously relied upon reference is relied upon to teach these limitations.
The rejection under 35 USC 103 is maintained.
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 76, 77, 79-92, and 94-108 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more. Claims 76, 77, and 79-90 are drawn to a system, claims 91, 92, 94-105, 107, and 108 are drawn to a method, and claim 106 is drawn to a non-transitory computer readable medium, each of which is within the four statutory categories.
Step 2A(1)
Claim 76 recites, in part, performing the steps of
receiving clinical data of a subject and a set of treatment options for a disease or disorder of the subject, wherein the disease or disorder comprises cancer, and wherein the set of treatment options comprises one or more biochemical interventions configured to treat the cancer;
determining probabilistic predictions of clinical outcomes of the set of treatment options based at least in part on clinical data of test subjects, wherein the clinical outcomes comprise future uncertainty;
determine a plurality of treatment features for the one or more biochemical interventions, wherein the plurality of treatment features comprises a chemical structure and a biological target of the one or more biochemical interventions; and
using at least the clinical data of the subject and the plurality of treatment features of the one or more biochemical interventions to determine probabilistic predictions of clinical outcomes in response to the one or more biochemical interventions of the set of treatment options configured to treat the cancer of the subject.
These elements amount to a form of managing personal behavior or relationships or interactions between people, and therefore fall within the scope of a method of organizing human activity. Fundamentally the process is that of predicting clinical outcomes for plurality of biochemical interventions for treating a subject’s cancer based on the subject’s clinical information, biological targets of the interventions, and clinical outcomes of other patients. These steps encompass clinical research for and clinicians selecting drugs for treating cancer patients based on information about the patient and known effects in patient populations.
Claim 106 recites similar limitations and also recites an abstract idea under the same analysis.
Claim 91 recites, in part, performing the steps of
receiving clinical data of a subject and a set of treatment options for a disease or disorder of the subject, wherein the disease or disorder comprises cancer, and wherein the set of treatment options comprises one or more biochemical interventions configured to treat the cancer;
determining probabilistic predictions of clinical outcomes of the set of treatment options based at least in part on clinical data of test subjects, wherein the clinical outcomes comprise future uncertainty;
determine a plurality of treatment features for the one or more biochemical interventions, wherein the plurality of treatment features comprises a chemical structure and a biological target of the one or more biochemical interventions; and
using at least the clinical data of the subject and the plurality of treatment features of the one or more biochemical interventions to determine probabilistic predictions of clinical outcomes in response to the one or more biochemical interventions of the set of treatment options configured to treat the cancer of the subject; and
administering a selected subset of the one or more biochemical interventions to the subject, wherein the subset is selected based at least in part on the determined probabilistic predictions of clinical outcomes.
These elements amount to a form of managing personal behavior or relationships or interactions between people, and therefore fall within the scope of a method of organizing human activity. Fundamentally the process is that of treating a patient’s cancer by predicting clinical outcomes for plurality of biochemical treatment interventions based on the subject’s clinical information, biological targets of the interventions, and clinical outcomes of other patients. These steps encompass clinical research for and clinicians selecting drugs for treating cancer patients based on information about the patient and known effects in patient populations.
Step 2A(2)
This judicial exception is not integrated into a practical application because the additional elements within the claims only amount to:
A. Instructions to Implement the Judicial Exception. MPEP 2106.05(f)
Claim 76 recites additional elements of a) a storage device used to store instructions and a computer processor recited as executing the instructions to perform the subsequent data processing functions, and b) a prediction module comprising a trained machine learning model used to determine the probabilistic predictions of clinical outcomes based on the test subjects, to determine the plurality of treatment features, and to predict the clinical outcomes using the clinical data of the subject and plurality of treatment features.
Claim 91 recites additional elements of a) a prediction module comprising a trained machine learning model used to determine the probabilistic predictions of clinical outcomes based on the test subjects, to determine the plurality of treatment features, and to predict the clinical outcomes using the clinical data of the subject and plurality of treatment features.
Claim 106 recites additional elements of a) a non-transitory computer readable medium used to store instructions and a computer processor recited as executing the instructions to perform the subsequent data processing functions, and b) a prediction module comprising a trained machine learning model used to determine the probabilistic predictions of clinical outcomes based on the test subjects, to determine the plurality of treatment features, and to predict the clinical outcomes using the clinical data of the subject and plurality of treatment features.
Paragraphs 181-184, 189, and 190 of Applicant’s specification as originally filed describe a computer system having a computer processor and memory, describing the processor as encompassing CPUs and other integrated circuits and the memory as comprising forms of storage and non-transitory media such as RAM, CDROM, hard disks, and flash memory. Paragraph 110 further describes the system as comprising modules including a prediction module. The computer processor, memory, non-transitory computer readable medium, and prediction module are each therefore construed as encompassing generic forms of computing devices.
Paragraphs 53 and 54 describe the trained machine learning model as any of a plurality of different algorithms including a Bayesian model, a support vector machine (SVM), a linear regression, a logistic regression, a random forest, a neural network, and multilevel statistical model. The trained machine learning model is construed accordingly as encompassing general purpose forms of machine learning algorithms.
The above elements only amount to mere instructions to implement functions within the abstract idea using computing elements as tools. Each of the computer processor, storage device, non-transitory computer readable medium, and predictor module are recited at a high level of generality as implementing functions such as storing instructions and performing data processing steps, and are disclosed broadly as encompassing generic computing elements. The trained machine learning model is similarly recited at a high level of generality as used to determine the probabilistic predictions of clinical outcomes and the plurality of treatment features, and is disclosed as encompassing a plurality of different potential types of algorithms. These elements are not sufficient to integrate the abstract idea into a practical application.
The above claims, as a whole, are therefore directed to an abstract idea.
Step 2B
The present claims do not include additional elements that are sufficient to amount to more than the abstract idea because the additional elements or combination of elements amount to no more than a recitation of:
A. Instructions to Implement the Judicial Exception. MPEP 2106.05(f)
As explained above, claims 76, 91, and 106 only recite the storage device, computer processor, non-transitory computer readable medium, prediction module, and trained machine learning model as tools for performing the steps of the abstract idea, and mere instructions to perform the abstract idea using a computer is not sufficient to amount to significantly more than the abstract idea. MPEP 2106.05(f)
Thus, taken alone, the additional elements do not amount to significantly more than the above-identified judicial exception. Looking at the limitations as an ordered combination adds nothing that is not already present when looking at the elements taken individually.
Depending Claims
Dependent claims 77-90 and 92-105 are directed to the judicial exception as explained above for Claims 76 and 91 and are further directed to limitations directed to the collection of clinical data as related to mutations and other related variables, cancer, the determination of a wide range of treatment options, the use of machine learning processes to determine clinical outcome predictions, the generation of electronic reports and the determination of probabilistic predictions of clinical outcomes as related to a variety of treatment options. These limitations or processes are considered to be executed by the general-purpose computing system as explained above, and therefore do not result in the claimed invention being directed to a practical application or comprise significantly more than the identified abstract idea.
Dependent claims 77-90 and 92-105 do not add more to the abstract idea of independent Claims 76 and 91 and therefore are rejected as ineligible subject matter under 35 U.S.C. 101 based on a rationale similar to the claims from which they depend.
Claims 76, 77, 79-92, and 94-108 are therefore rejected under 35 U.S.C. 101 as being directed to non-statutory subject matter.
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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 76, 77, 79-88, 91, 92, 94-103, and 106-108 are rejected under 35 U.S.C. 103 as being unpatentable over Lipsky et al (US Patent Application Publication 2021/0104321) in view of Spetzler et al (US Patent Application Publication 2020/0024669) and Shrager et al (WO 2019/144116).
With respect to claim 76, Lipsky discloses the claimed system comprising a computer processor and a storage device having instructions stored thereon that are operable, when executed by the computer processor ([156] and [400]-[406]), to cause the computer processor to:
(ii) access a prediction module comprising a trained machine learning model that determines probabilistic predictions of clinical outcomes of a set of treatment options for a disease or disorder, wherein the disease or disorder comprises cancer ([346] describes the disease as comprising a cancer), wherein the set of treatment options comprises one or more biochemical interventions configured to treat the cancer based at least in part on clinical data of test subjects wherein the clinical outcomes comprise future uncertainty ([114], [115], [452, 477, 480, 487, 488, 607]; [170, 171, 346 "disease may comprise an acute disease, a chronic disease, a clinical disease, a flare-up disease, a progressive disease, a refractory disease, a subclinical disease, or a terminal," 470, 481 "plurality of input variables or features may also include clinical information of a subject, such as health data. For example, the health data of a subject may comprise one or more of: a diagnosis of one or more conditions (e.g., a disease or disorder, such as a lupus condition), a prognosis of one or more conditions (e.g., a disease or disorder, such as a lupus condition), a risk of having one or more conditions (e.g., a disease or disorder, such as a lupus condition), a treatment history of one or more conditions," 482, 483, 489 "independent training samples may comprise a sample from a subject, associated datasets obtained by assaying the sample (as described elsewhere herein), and one or more known output values or classes of individuals corresponding to the sample (e.g., a clinical diagnosis, prognosis, absence, or treatment efficacy of a condition of the subject)," 487, 488, 607 "identifying the subject as having one or more conditions (e.g., a disease or disorder, such as a lupus condition), the subject may be optionally provided with a therapeutic intervention (e.g., prescribing an appropriate course of treatment to treat the one or more conditions of the subject). The therapeutic intervention may comprise a prescription of an effective dose of a drug, a further testing or evaluation of the condition, a further monitoring of the condition, or a combination thereof, 498, 613-618]);
(iv) apply the prediction module to at least the clinical data of the subject to determine probabilistic predictions of clinical outcomes in response to the one or more biochemical interventions of the set of treatment options configured to treat the cancer of the subject ([452 "diagnose" or "diagnosis" of a status or outcome includes predicting or diagnosing the status or outcome, determining predisposition to a status or outcome, monitoring treatment of patient, diagnosing a therapeutic response of a patient, and prognosis of status or outcome, progression," 477, 480 "plurality of input variables or features may comprise one or more datasets indicative of the presence (e.g., positive test result) or absence (e.g., negative test result) of one or more conditions (e.g., a disease or disorder," 487, 488, 607 "identifying the subject as having one or more conditions (e.g., a disease or disorder, such as a lupus condition), the subject may be optionally provided with a therapeutic intervention (e.g., prescribing an appropriate course of treatment to treat the one or more conditions of the subject). The therapeutic intervention may comprise a prescription of an effective dose of a drug, a further testing or evaluation of the condition, a further monitoring of the condition, or a combination thereof. If the subject is currently being treated for the condition with a course of treatment, the therapeutic intervention may comprise a subsequent different course of treatment (e.g., to increase treatment efficacy due to non-efficacy of the current course of treatment),"]);
Lipsky does not explicitly disclose however Spetzler discloses:
(i) receive clinical data of a subject and a set of treatment options for a disease or disorder of the subject, wherein the set of treatment options corresponds to clinical outcomes having future uncertainty ([235 “clinical citations are assessed for their relevance to the methods of the invention using a hierarchy derived from the evidence grading system used by the United States Preventive Services Taskforce. The “best evidence” can be used as the basis for a rule. The simplest rules are constructed in the format of “if biomarker positive then treatment option one, else treatment option two.” Treatment options comprise no treatment with a specific drug, treatment with a specific drug or treatment with a combination of drugs. In some embodiments, more complex rules are constructed that involve the interaction of two or more biomarkers,” 328 “comprehensive profile may be used to assist in treatment selection for highly aggressive or rare tumors with uncertain treatment regimens. For example, a comprehensive profile can be used to identify a candidate treatment for a newly diagnosed case or when the patient has exhausted standard of care therapies or has an aggressive disease,” 359 “clinical trials that are matched may be identified based on results of “pathogenic,” “presumed pathogenic,” or variant of uncertain (or unknown) significance (“VUS”). In some embodiments, the decision to incorporate/associate a drug class with a biomarker mutation can further depend on one or more of the following: 1) Clinical evidence; 2) Preclinical evidence; 3) Understanding of the biological pathway affected by the biomarker; and 4) expert analysis,” 419 “displays a summary of therapies associated with potential benefit, therapies associated with uncertain benefit, and therapies associated with potential lack of benefit….potential benefit for treating the patient's breast cancer because the sample was determined to be MSI high based on analysis with NGS. FIG. 27H illustrates more detailed information for biomarker profiling used to associate agents with uncertain benefit. The report notes that therapies are placed in the uncertain benefit category when a result suggests only a decreased likelihood of response,”]).
Therefore it would be obvious for Lipsky wherein the caregivers receive clinical data of a subject and a set of treatment options for a disease or disorder of the subject, wherein the set of treatment options corresponds to clinical outcomes having future uncertainty as per the steps to Spetzler in order to determine treatment options which include levels of determined future uncertainty in order to provide patients and caregivers with a set of options to enable the optimal selection of treatment options to account for levels of certainty and uncertainty and thereby result in the optimization of treatments provided to patients.
Shrager further teaches that it was old and well known in the art before the effective filing date of the claimed invention to determine, by a trained machine learning model, a plurality of treatment features for the one or more biochemical interventions, wherein the plurality of treatment features comprises a chemical structure and a biological target of the one or more biochemical interventions, and apply a prediction module to at least clinical data of a subject and the plurality of treatment features of the one or more biochemical interventions to determine probabilistic predictions of clinical outcomes in response to the one or more biochemical interventions ([61], [62], [69], [73]-[75], [78], and [92] describe using a trained machine learning model to evaluate a plurality of potential drug treatment options for use in treating a patient based on molecule and target as well as patient clinical data; Figure 7 shows an example output of therapies)
Therefore it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Lipsky to determine, by a trained machine learning model, a plurality of treatment features for the one or more biochemical interventions, wherein the plurality of treatment features comprises a chemical structure and a biological target of the one or more biochemical interventions, and apply a prediction module to at least clinical data of a subject and the plurality of treatment features of the one or more biochemical interventions to determine probabilistic predictions of clinical outcomes in response to the one or more biochemical interventions as taught by Shrager since the claimed invention is only a combination of these old and well known elements which would have performed the same function in combination as each did separately. In the present case Lipsky already discloses a trained machine learning model and determining probabilistic predictions of outcomes for different drug treatments, and further performing the steps above taught by Shrager would yield those same functions in Lipsky, making the results predictable to one of ordinary skill in the art (MPEP 2143).
With respect to claim 77, Lipsky/Spetzler/Shrager teach the system of claim 76.
Lipsky does not explicitly disclose however Spetzler discloses wherein the clinical data is selected from somatic genetic mutations ([Table 4, 356 “cancer genes disclosed in the COSMIC (Catalogue Of Somatic Mutations In Cancer) database,”]), germline genetic mutations ([Table 4, 391, 457 “Tumors are classified as MMR-deficient (dMMR) if they have somatic or germline mutations,”]), mutational burden ([6 “biomarkers include without limitation microsatellite instability (MSI), tumor mutational burden (TMB, also referred to as tumor mutation load,”]), protein levels ([19 “profiling can comprise any useful technique, including without limitation determining: i) a protein expression level, wherein optionally the protein expression level is determined using IHC, flow cytometry or an immunoassay;”]), transcriptome levels ([134 “expression levels of nearly all transcripts can be quantitatively determined; the abundance of signatures is representative of the expression level of the gene in the analyzed tissue,” 136]), metabolite levels ([102 “Circulating biomarkers according to the invention include any appropriate biomarker that can be detected in bodily fluid, including without limitation protein, nucleic acids, e.g., DNA, mRNA and microRNA, lipids, carbohydrates and metabolites,”]), tumor size or staging ([311 “performing tumor profiling on a tumor sample from a subject comprising the selected methods to determine the status of the characteristic of each of the biomarkers; and compiling the status in a report according to said priority list; thereby generating a report that identifies a tumor profile,” 312-323]), clinical symptoms ([76 “beneficial or desired clinical results include, but are not limited to, alleviation or amelioration of one or more symptoms, diminishment of extent of disease, stabilized (i.e., not worsening) state of disease, preventing spread of disease,” 80 “Samples can be associated with relevant information such as age, gender, and clinical symptoms present in the subject; source of the sample; and methods of collection and storage of the sample,”]), laboratory test results ([82, 296 “clinical information management system includes the laboratory information management system and the medical information contained in the data warehouses and databases includes medical information libraries,” 299, 310]), and clinical history ([47 “Rules of the invention aide prioritizing treatment, e.g., direct results of molecular profiling, anticipated efficacy of therapeutic agent, prior history with the same or other treatments, expected side effects, availability of therapeutic agent, cost of therapeutic agent, drug-drug interactions, and other factors considered by a treating physician,” 259, 293, 295]).
Therefore it would be obvious for Lipsky wherein the clinical data is selected from somatic genetic mutations, germline genetic mutations, mutational burden, protein levels, transcriptome levels, metabolite levels, tumor size or staging, clinical symptoms, laboratory test results, and clinical history as per the steps to Spetzler in order to determine treatment options which include levels of determined future uncertainty in order to provide patients and caregivers with a set of options to enable the optimal selection of treatment options to account for levels of certainty and uncertainty and thereby result in the optimization of treatments provided to patients.
With respect to claim 79, Lipsky/Spetzler/Shrager teach the system of claim 76.
Lipsky does not explicitly disclose however Spetzler discloses wherein (iii) comprises applying the prediction module to determine interaction terms between the clinical data of the subject and the plurality of treatment features of the one or more biochemical interventions, to determine the probabilistic predictions of the clinical outcomes in response to the one or more biochemical interventions ([248 “treatment options are presented in a prioritized list. In some embodiments, the treatment options are presented without prioritization information. In either case, an individual, e.g., the treating physician or similar caregiver may choose from the available options,” 296 “an illustrative clinical decision support system of the information-based personalized medicine drug discovery system and method… information management systems relating to particular patients and the medical information databases and data warehouses come together at a data junction center where diagnostic information and therapeutic options can be obtained,” 303, 305 “report can further comprise a list describing the expected benefit of the plurality of treatment options based on the assessed characteristics, thereby identifying candidate treatment options for the subject,” 307-309]).
Therefore it would be obvious for Lipsky wherein (iii) comprises applying the prediction module to determine interaction terms between the clinical data of the subject and the plurality of treatment features of the one or more biochemical interventions, to determine the probabilistic predictions of the clinical outcomes in response to the one or more biochemical interventions as per the steps to Spetzler in order to determine treatment options which include levels of determined future uncertainty in order to provide patients and caregivers with a set of options to enable the optimal selection of treatment options to account for levels of certainty and uncertainty and thereby result in the optimization of treatments provided to patients.
With respect to claim 80, Lipsky/Spetzler/Shrager teach the system of claim 76.
Lipsky does not explicitly disclose however Spetzler discloses wherein the clinical outcomes having future uncertainty ([419 “summary of therapies associated with potential benefit, therapies associated with uncertain benefit, and therapies associated with potential lack of benefit…. detailed information for biomarker profiling used to associate agents with uncertain benefit. The report notes that therapies are placed in the uncertain benefit category when a result suggests only a decreased likelihood of response (vs. little to no likelihood of response),”]) comprise a change in tumor size ([81 “the size and type of the tumor (e.g., solid or suspended, blood or ascites), among other factors,” 254 “decrease in size or number of the lesions by 30% or more. Stable disease (SD) refers to a disease that has remained relatively unchanged in size and number of lesions. Generally, less than a 50% decrease or a slight increase in size would be described as stable disease. Progressive disease (PD) means that the disease has increased in size or number on treatment,”]), a change in patient functional status ([258 “other functional aspects of the systems (and components of the individual operating components of the systems) may not be described in detail herein but are part of the invention. Furthermore, the connecting lines shown in the various figures contained herein are intended to represent illustrative functional relationships and/or physical couplings between the various elements. It should be noted that many alternative or additional functional relationships or physical connections,” 280-282]), a time-to- disease progression ([4 “some patients have very limited options after their tumor has progressed in spite of front line, second line and sometimes third line and beyond) therapies,” 21]), a time-to-treatment failure ([250 “Progression-free survival rates are an indication of the effectiveness of a particular treatment. Similarly, disease-free survival (DFS) denotes the chances of staying free of disease after initiating a particular treatment for an individual or a group of individuals suffering from a cancer,” 251-254]), or a progression-free survival time ([76 “delay or slowing of disease progression, amelioration or palliation of the disease state, and remission (whether partial or total), whether detectable or undetectable. Treatment also includes prolonging survival as compared to expected survival if not receiving treatment or if receiving a different treatment,” 250, 251]).
Therefore it would be obvious for Lipsky wherein the clinical outcomes having future uncertainty comprise a change in tumor size, a change in patient functional status, a time-to- disease progression, a time-to-treatment failure, overall survival, or progression-free survival as per the steps to Spetzler in order to determine treatment options which include levels of determined future uncertainty in order to provide patients and caregivers with a set of options to enable the optimal selection of treatment options to account for levels of certainty and uncertainty and thereby result in the optimization of treatments provided to patients.
With respect to claim 81, Lipsky/Spetzler/Shrager teach the system of claim 76. Lipsky further discloses:
wherein the probabilistic predictions of clinical outcomes of the set of treatment options comprise statistical distributions of the clinical outcomes of the set of treatment options ([452 “term “diagnose” or “diagnosis” of a status or outcome includes predicting or diagnosing the status or outcome, determining predisposition to a status or outcome, monitoring treatment of patient, diagnosing a therapeutic response of a patient, and prognosis of status or outcome, progression, and response to particular treatment,” 477 “individuals not having the condition (e.g., healthy individuals, or individuals who do not have a lupus condition), in order to classify a subject as having the condition (e.g., positive test outcome) or not having the condition (e.g., negative test outcome),” 499]).
With respect to claim 82, Lipsky/Spetzler/Shrager teach the system of claim 76. Lipsky further discloses:
wherein the probabilistic predictions of clinical outcomes of the set of treatment options are explainable based on performing a query of the probabilistic predictions ([338 “predictive tool for evaluating patient at both the chemical and cellular levels to advance personalized treatment. Data analytical techniques such as machine learning enable proper correlation between genetic records and phenotypes,” 452 “monitoring treatment of patient, diagnosing a therapeutic response of a patient, and prognosis of status or outcome, progression, and response to particular treatment,” 454, 956 “machine learning approaches to integrate gene expression data from multiple SLE data sets and used it to predict active disease. Both raw whole blood gene expression data and informative gene modules generated by Weighted Gene Co-expression Network Analysis from purified leukocyte populations are employed by classification algorithms. SLE whole blood gene expression data from 156 patients across three data sets are used to classify patients as having active or inactive disease as characterized by standard clinical composite outcome measures,”]).
With respect to claim 83, Lipsky/Spetzler/Shrager teach the system of claim 76. Lipsky further discloses:
wherein the instructions are operable, when executed by the computer processor, to cause the computer processor to further apply a training module that trains the trained machine learning model, wherein the training module updates the trained machine learning model using the probabilistic predictions of the clinical outcomes of the set of treatment options generated in (iv) ([477 “Feature sets may be generated from datasets obtained using one or more assays of a biological sample, and a trained algorithm may be used to process one or more of the feature sets to identify or assess the condition (e.g., a disease or disorder, such as a lupus condition). For example, the trained algorithm may be used to apply a machine learning classifier to a plurality of lupus condition-associated or interferon-associated genomic loci that are associated with two or more classes of individuals inputted into a machine learning model, in order to classify a subject into one of the two or more classes of individuals. For example, the trained algorithm may be used to apply a machine learning classifier to a plurality of lupus condition-associated or interferon-associated genomic loci that are associated with individuals with known conditions (e.g., a disease or disorder, such as a lupus condition) and individuals not having the condition (e.g., healthy individuals, or individuals who do not have a lupus condition), in order to classify a subject as having the condition (e.g., positive test outcome) or not having the condition (e.g., negative test outcome),” 478-483, 489-491, 498 “Classifiers of the trained algorithm may be adjusted or tuned to improve or optimize one or more performance metrics, such as accuracy, PPV, NPV, clinical sensitivity, clinical specificity, AUC, or a combination thereof (e.g., a performance index incorporating a plurality of such performance metrics, such as by calculating a weight sum therefrom), of identifying the presence (e.g., positive test result) or absence (e.g., negative test result) of the condition. The classifiers may be adjusted or tuned by adjusting parameters of the classifiers (e.g., a set of cutoff values used to classify a sample as described elsewhere herein, or weights of a neural network) to improve or optimize the performance metrics,”]).
With respect to claim 84, Lipsky/Spetzler/Shrager teach the system of claim 76. Lipsky further discloses:
wherein the trained machine learning model is selected from the group consisting of a Bayesian model, a support vector machine (SVM), a linear regression, a logistic regression, a random forest, and a neural network ([358 “normalizing is performed by Robust Multi-Array Analysis (RMA), Guanine Cytosine Robust Multi-Array Analysis (GCRMA), Linear Models for Microarray Data, variance stabilizing transformation (VST), normal-exponential quantile correction (NEQC),” 359 “variance correction comprises employing a local empirical Bayesian shrinkage, adjusting the p-values for multiple hypothesis testing using the Benjamini-Hochberg correction,” 479 “trained algorithm may comprise a machine learning algorithm, such as a supervised machine learning algorithm. The supervised machine learning algorithm may comprise, for example, a Random Forest, a support vector machine (SVM), a neural network, or a deep learning algorithm. The trained algorithm may comprise a classification and regression tree (CART) algorithm. The trained algorithm may comprise an unsupervised machine learning algorithm,” 480-483]).
With respect to claim 85, Lipsky/Spetzler/Shrager teach the system of claim 76,
Lipsky does not explicitly disclose however Spetzler discloses wherein the trained machine learning model comprises a multilevel statistical model that accounts for variation at a plurality of distinct levels of analysis or correlation of subject-level effects across the plurality of distinct levels of analysis ([46 “identifying targets for drugs that may be effective for a given cancer. For example, the candidate treatment can be a treatment known to have an effect on cells that differentially express genes as identified by molecular profiling techniques, an experimental drug, a government or regulatory approved drug or any combination of such drugs,” 47, 76 “treatment can include administration of a therapeutic agent, which can be an agent that exerts a cytotoxic, cytostatic, or immunomodulatory effect on diseased cells, e.g., cancer cells, or other cells that may promote a diseased state, e.g., activated immune cells. Therapeutic agents selected by the methods of the invention are not limited. Any therapeutic agent can be selected where a link can be made between molecular profiling and potential efficacy of the agent. Therapeutic agents include without limitation drugs, pharmaceuticals, small molecules, protein therapies, antibody therapies, viral therapies, gene therapies, and the like. Cancer treatments or therapies include apoptosis-mediated and non-apoptosis mediated cancer therapies including, without limitation, chemotherapy, hormonal therapy, radiotherapy, immunotherapy,” 236, 250 “Progression-free survival rates are an indication of the effectiveness of a particular treatment. Similarly, disease-free survival (DFS) denotes the chances of staying free of disease after initiating a particular treatment for an individual or a group of individuals suffering from a cancer. It can refer to the percentage of individuals in a group who are likely to be free of disease after a specified duration of time. Disease-free survival rates are an indication of the effectiveness of a particular treatment,” 254 “The effectiveness of a treatment can be monitored by other measures. A complete response (CR) comprises a complete disappearance of the disease: no disease is evident on examination, scans or other tests. A partial response (PR) refers to some disease remaining in the body, but there has been a decrease in size or number of the lesions by 30% or more,”]).
Therefore it would be obvious for Lipsky wherein the trained machine learning model comprises a multilevel statistical model that accounts for variation at a plurality of distinct levels of analysis or correlation of subject-level effects across the plurality of distinct levels of analysis as per the steps to Spetzler in order to determine treatment options which include levels of determined future uncertainty in order to provide patients and caregivers with a set of options to enable the optimal selection of treatment options to account for levels of certainty and uncertainty and thereby result in the optimization of treatments provided to patients.
With respect to claim 86, Lipsky/Spetzler/Shrager teach the system of claim 85. Lipsky further discloses:
wherein the multilevel statistical model comprises a generalized linear model ([4 “the classifier comprises an elastic generalized linear model classifier, a k-nearest neighbors classifier, a random forest classifier, 5, 17]).
With respect to claim 87, Lipsky/Spetzler/Shrager teach the system of claim 86. Lipsky further discloses:
wherein the generalized linear model comprises use of the expression: η = X · β + Z · u wherein η is a linear response, X is a vector of predictors for treatment effects fixed across subjects, β is a vector of fixed effects, Z is a vector of predictors for subject-level treatment effects, and u is a vector of subject-level effects ([40 “supervised machine learning algorithm comprises a deep learning algorithm, a support vector machine (SVM), a neural network, or a Random Forest,” 348 “biased algorithm may comprise Gene Set Enrichment Analysis (GSVA) enrichment of phenotype-associated cell-specific modules. The unbiased approach may employ all available phenotypic data. The machine learning algorithm may comprise an elastic generalized linear model (GLM), a k-nearest neighbors classifier (KNN), a random forest (RF) classifier, or any combination thereof. GLM, KNN, and RF machine learning algorithms may be performed using the glmnet, caret, and randomForest R packages,” 351 “GLM algorithm may carry out logistic regression with a tunable elastic penalty term to find a balance between an L1 (LASSO) and an L2 (ridge), whereby penalties facilitate variable selection in order to generate sparse solutions. Least Absolute Shrinkage and Selection Operator (LASSO) is a regularization feature selection technique to reduce overfitting in regression problems. Ridge regression employs a penalty term is to shrink the LASSO coefficient values,”353, 358-360, 479 “trained algorithm may comprise a machine learning algorithm, such as a supervised machine learning algorithm. The supervised machine learning algorithm may comprise, for example, a Random Forest, a support vector machine (SVM), a neural network, or a deep learning algorithm. The trained algorithm may comprise a classification and regression tree (CART) algorithm,”]). Examiner Note: Examiner as cited to above with respect to the disclosures of Lipsky interprets the implementation of a wide range of trained machine learning algorithms which are implemented in detail throughout the disclosures of Lipsky to detail, as would be understood by a person of skill in the art to disclose the implementation of generalized linear model executions. Therefore Examiner interprets the disclosures of Lipsky to detail the claimed formula as would be understood by a person of skill in the art.
With respect to claim 88, Lipsky/Spetzler/Shrager teach the system of claim 86. Lipsky further discloses:
wherein the generalized linear model comprises use of the expression: y = g -1 (η) wherein η is a linear response, g is an appropriately chosen link function from observed data to the linear response, and y is an outcome variable of interest ([40 “supervised machine learning algorithm comprises a deep learning algorithm, a support vector machine (SVM), a neural network, or a Random Forest,” 348 “biased algorithm may comprise Gene Set Enrichment Analysis (GSVA) enrichment of phenotype-associated cell-specific modules. The unbiased approach may employ all available phenotypic data. The machine learning algorithm may comprise an elastic generalized linear model (GLM), a k-nearest neighbors classifier (KNN), a random forest (RF) classifier, or any combination thereof. GLM, KNN, and RF machine learning algorithms may be performed using the glmnet, caret, and randomForest R packages,” 351 “GLM algorithm may carry out logistic regression with a tunable elastic penalty term to find a balance between an L1 (LASSO) and an L2 (ridge), whereby penalties facilitate variable selection in order to generate sparse solutions. Least Absolute Shrinkage and Selection Operator (LASSO) is a regularization feature selection technique to reduce overfitting in regression problems. Ridge regression employs a penalty term is to shrink the LASSO coefficient values,”353, 358-360, 479 “trained algorithm may comprise a machine learning algorithm, such as a supervised machine learning algorithm. The supervised machine learning algorithm may comprise, for example, a Random Forest, a support vector machine (SVM), a neural network, or a deep learning algorithm. The trained algorithm may comprise a classification and regression tree (CART) algorithm,”]). Examiner Note: Examiner as cited to above with respect to the disclosures of Lipsky interprets the implementation of a wide range of trained machine learning algorithms which are implemented in detail throughout the disclosures of Lipsky to detail, as would be understood by a person of skill in the art to disclose the implementation of generalized linear model executions. Therefore Examiner interprets the disclosures of Lipsky to detail the claimed formula as would be understood by a person of skill in the art.
With respect to claim 91, Lipsky discloses the claimed method comprising:
(ii) accessing a prediction module comprising a trained machine learning model that determines probabilistic predictions of clinical outcomes of a set of treatment options for a disease or disorder, wherein the disease or disorder comprises cancer ([346] describes the disease as comprising a cancer), wherein the set of treatment options comprises one or more biochemical interventions configured to treat the cancer based at least in part on clinical data of test subjects wherein the clinical outcomes comprise future uncertainty ([114], [115], [452, 477, 480, 487, 488, 607]; [170, 171, 346 "disease may comprise an acute disease, a chronic disease, a clinical disease, a flare-up disease, a progressive disease, a refractory disease, a subclinical disease, or a terminal," 470, 481 "plurality of input variables or features may also include clinical information of a subject, such as health data. For example, the health data of a subject may comprise one or more of: a diagnosis of one or more conditions (e.g., a disease or disorder, such as a lupus condition), a prognosis of one or more conditions (e.g., a disease or disorder, such as a lupus condition), a risk of having one or more conditions (e.g., a disease or disorder, such as a lupus condition), a treatment history of one or more conditions," 482, 483, 489 "independent training samples may comprise a sample from a subject, associated datasets obtained by assaying the sample (as described elsewhere herein), and one or more known output values or classes of individuals corresponding to the sample (e.g., a clinical diagnosis, prognosis, absence, or treatment efficacy of a condition of the subject)," 487, 488, 607 "identifying the subject as having one or more conditions (e.g., a disease or disorder, such as a lupus condition), the subject may be optionally provided with a therapeutic intervention (e.g., prescribing an appropriate course of treatment to treat the one or more conditions of the subject). The therapeutic intervention may comprise a prescription of an effective dose of a drug, a further testing or evaluation of the condition, a further monitoring of the condition, or a combination thereof, 498, 613-618]);
(iv) applying the prediction module to at least the clinical data of the subject to determine probabilistic predictions of clinical outcomes in response to the one or more biochemical interventions of the set of treatment options configured to treat the cancer of the subject ([452 "diagnose" or "diagnosis" of a status or outcome includes predicting or diagnosing the status or outcome, determining predisposition to a status or outcome, monitoring treatment of patient, diagnosing a therapeutic response of a patient, and prognosis of status or outcome, progression," 477, 480 "plurality of input variables or features may comprise one or more datasets indicative of the presence (e.g., positive test result) or absence (e.g., negative test result) of one or more conditions (e.g., a disease or disorder," 487, 488, 607 "identifying the subject as having one or more conditions (e.g., a disease or disorder, such as a lupus condition), the subject may be optionally provided with a therapeutic intervention (e.g., prescribing an appropriate course of treatment to treat the one or more conditions of the subject). The therapeutic intervention may comprise a prescription of an effective dose of a drug, a further testing or evaluation of the condition, a further monitoring of the condition, or a combination thereof. If the subject is currently being treated for the condition with a course of treatment, the therapeutic intervention may comprise a subsequent different course of treatment (e.g., to increase treatment efficacy due to non-efficacy of the current course of treatment),"]);
Lipsky does not explicitly disclose however Spetzler discloses:
(i) receiving clinical data of a subject and a set of treatment options for a disease or disorder of the subject, wherein the set of treatment options corresponds to clinical outcomes having future uncertainty ([235 “clinical citations are assessed for their relevance to the methods of the invention using a hierarchy derived from the evidence grading system used by the United States Preventive Services Taskforce. The “best evidence” can be used as the basis for a rule. The simplest rules are constructed in the format of “if biomarker positive then treatment option one, else treatment option two.” Treatment options comprise no treatment with a specific drug, treatment with a specific drug or treatment with a combination of drugs. In some embodiments, more complex rules are constructed that involve the interaction of two or more biomarkers,” 328 “comprehensive profile may be used to assist in treatment selection for highly aggressive or rare tumors with uncertain treatment regimens. For example, a comprehensive profile can be used to identify a candidate treatment for a newly diagnosed case or when the patient has exhausted standard of care therapies or has an aggressive disease,” 359 “clinical trials that are matched may be identified based on results of “pathogenic,” “presumed pathogenic,” or variant of uncertain (or unknown) significance (“VUS”). In some embodiments, the decision to incorporate/associate a drug class with a biomarker mutation can further depend on one or more of the following: 1) Clinical evidence; 2) Preclinical evidence; 3) Understanding of the biological pathway affected by the biomarker; and 4) expert analysis,” 419 “displays a summary of therapies associated with potential benefit, therapies associated with uncertain benefit, and therapies associated with potential lack of benefit….potential benefit for treating the patient's breast cancer because the sample was determined to be MSI high based on analysis with NGS. FIG. 27H illustrates more detailed information for biomarker profiling used to associate agents with uncertain benefit. The report notes that therapies are placed in the uncertain benefit category when a result suggests only a decreased likelihood of response,”]).
Therefore it would be obvious for Lipsky wherein the caregivers receive clinical data of a subject and a set of treatment options for a disease or disorder of the subject, wherein the set of treatment options corresponds to clinical outcomes having future uncertainty as per the steps to Spetzler in order to determine treatment options which include levels of determined future uncertainty in order to provide patients and caregivers with a set of options to enable the optimal selection of treatment options to account for levels of certainty and uncertainty and thereby result in the optimization of treatments provided to patients.
Shrager further teaches that it was old and well known in the art before the effective filing date of the claimed invention to determine, by a trained machine learning model, a plurality of treatment features for the one or more biochemical interventions, wherein the plurality of treatment features comprises a chemical structure and a biological target of the one or more biochemical interventions, and apply a prediction module to at least clinical data of a subject and the plurality of treatment features of the one or more biochemical interventions to determine probabilistic predictions of clinical outcomes in response to the one or more biochemical interventions ([61], [62], [69], [73]-[75], [78], and [92] describe using a trained machine learning model to evaluate a plurality of potential drug treatment options for use in treating a patient based on molecule and target as well as patient clinical data; Figure 7 shows an example output of therapies), and administering a selected subset of the one or more biochemical interventions to the subject, wherein the subset is selected based at least in part on the probabilistic predictions of clinical outcomes (Figure 7 shows an example output of therapies; [96] describes administering a selected one of the suggested therapies).
Therefore it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Lipsky to determine, by a trained machine learning model, a plurality of treatment features for the one or more biochemical interventions, wherein the plurality of treatment features comprises a chemical structure and a biological target of the one or more biochemical interventions, and apply a prediction module to at least clinical data of a subject and the plurality of treatment features of the one or more biochemical interventions to determine probabilistic predictions of clinical outcomes in response to the one or more biochemical interventions, and administer a selected subset of the one or more biochemical interventions to the subject, wherein the subset is selected based at least in part on the probabilistic predictions of clinical outcomes as taught by Shrager since the claimed invention is only a combination of these old and well known elements which would have performed the same function in combination as each did separately. In the present case Lipsky already discloses a trained machine learning model and determining probabilistic predictions of outcomes for different drug treatments, and further performing the steps above taught by Shrager would yield those same functions in Lipsky, making the results predictable to one of ordinary skill in the art (MPEP 2143).
Claim 92 recites limitations similar to those recited in claim 77, and is rejected on the same grounds set out above with respect to claim 77.
Claim 94 recites limitations similar to those recited in claim 79, and is rejected on the same grounds set out above with respect to claim 79.
Claim 95 recites limitations similar to those recited in claim 80, and is rejected on the same grounds set out above with respect to claim 80.
Claim 96 recites limitations similar to those recited in claim 81, and is rejected on the same grounds set out above with respect to claim 81.
Claim 97 recites limitations similar to those recited in claim 82, and is rejected on the same grounds set out above with respect to claim 82.
Claim 98 recites limitations similar to those recited in claim 83, and is rejected on the same grounds set out above with respect to claim 83.
Claim 99 recites limitations similar to those recited in claim 84, and is rejected on the same grounds set out above with respect to claim 84.
Claim 100 recites limitations similar to those recited in claim 85, and is rejected on the same grounds set out above with respect to claim 85.
Claim 101 recites limitations similar to those recited in claim 86, and is rejected on the same grounds set out above with respect to claim 86.
Claim 102 recites limitations similar to those recited in claim 87, and is rejected on the same grounds set out above with respect to claim 87.
Claim 103 recites limitations similar to those recited in claim 88, and is rejected on the same grounds set out above with respect to claim 88.
With respect to claim 106, Lipsky discloses the claimed non-transitory computer storage medium storing instructions that are operable, when executed by computer processors, to cause the computer processor to implement a method ([395]-[397]) comprising:
(ii) accessing a prediction module comprising a trained machine learning model that determines probabilistic predictions of clinical outcomes of a set of treatment options for a disease or disorder, wherein the disease or disorder comprises cancer ([346] describes the disease as comprising a cancer), wherein the set of treatment options comprises one or more biochemical interventions configured to treat the cancer based at least in part on clinical data of test subjects wherein the clinical outcomes comprise future uncertainty ([114], [115], [452, 477, 480, 487, 488, 607]; [170, 171, 346 "disease may comprise an acute disease, a chronic disease, a clinical disease, a flare-up disease, a progressive disease, a refractory disease, a subclinical disease, or a terminal," 470, 481 "plurality of input variables or features may also include clinical information of a subject, such as health data. For example, the health data of a subject may comprise one or more of: a diagnosis of one or more conditions (e.g., a disease or disorder, such as a lupus condition), a prognosis of one or more conditions (e.g., a disease or disorder, such as a lupus condition), a risk of having one or more conditions (e.g., a disease or disorder, such as a lupus condition), a treatment history of one or more conditions," 482, 483, 489 "independent training samples may comprise a sample from a subject, associated datasets obtained by assaying the sample (as described elsewhere herein), and one or more known output values or classes of individuals corresponding to the sample (e.g., a clinical diagnosis, prognosis, absence, or treatment efficacy of a condition of the subject)," 487, 488, 607 "identifying the subject as having one or more conditions (e.g., a disease or disorder, such as a lupus condition), the subject may be optionally provided with a therapeutic intervention (e.g., prescribing an appropriate course of treatment to treat the one or more conditions of the subject). The therapeutic intervention may comprise a prescription of an effective dose of a drug, a further testing or evaluation of the condition, a further monitoring of the condition, or a combination thereof, 498, 613-618]);
(iv) applying the prediction module to at least the clinical data of the subject to determine probabilistic predictions of clinical outcomes in response to the one or more biochemical interventions of the set of treatment options configured to treat the cancer of the subject ([452 "diagnose" or "diagnosis" of a status or outcome includes predicting or diagnosing the status or outcome, determining predisposition to a status or outcome, monitoring treatment of patient, diagnosing a therapeutic response of a patient, and prognosis of status or outcome, progression," 477, 480 "plurality of input variables or features may comprise one or more datasets indicative of the presence (e.g., positive test result) or absence (e.g., negative test result) of one or more conditions (e.g., a disease or disorder," 487, 488, 607 "identifying the subject as having one or more conditions (e.g., a disease or disorder, such as a lupus condition), the subject may be optionally provided with a therapeutic intervention (e.g., prescribing an appropriate course of treatment to treat the one or more conditions of the subject). The therapeutic intervention may comprise a prescription of an effective dose of a drug, a further testing or evaluation of the condition, a further monitoring of the condition, or a combination thereof. If the subject is currently being treated for the condition with a course of treatment, the therapeutic intervention may comprise a subsequent different course of treatment (e.g., to increase treatment efficacy due to non-efficacy of the current course of treatment),"]);
Lipsky does not explicitly disclose however Spetzler discloses:
(i) receiving clinical data of a subject and a set of treatment options for a disease or disorder of the subject, wherein the set of treatment options corresponds to clinical outcomes having future uncertainty ([235 “clinical citations are assessed for their relevance to the methods of the invention using a hierarchy derived from the evidence grading system used by the United States Preventive Services Taskforce. The “best evidence” can be used as the basis for a rule. The simplest rules are constructed in the format of “if biomarker positive then treatment option one, else treatment option two.” Treatment options comprise no treatment with a specific drug, treatment with a specific drug or treatment with a combination of drugs. In some embodiments, more complex rules are constructed that involve the interaction of two or more biomarkers,” 328 “comprehensive profile may be used to assist in treatment selection for highly aggressive or rare tumors with uncertain treatment regimens. For example, a comprehensive profile can be used to identify a candidate treatment for a newly diagnosed case or when the patient has exhausted standard of care therapies or has an aggressive disease,” 359 “clinical trials that are matched may be identified based on results of “pathogenic,” “presumed pathogenic,” or variant of uncertain (or unknown) significance (“VUS”). In some embodiments, the decision to incorporate/associate a drug class with a biomarker mutation can further depend on one or more of the following: 1) Clinical evidence; 2) Preclinical evidence; 3) Understanding of the biological pathway affected by the biomarker; and 4) expert analysis,” 419 “displays a summary of therapies associated with potential benefit, therapies associated with uncertain benefit, and therapies associated with potential lack of benefit….potential benefit for treating the patient's breast cancer because the sample was determined to be MSI high based on analysis with NGS. FIG. 27H illustrates more detailed information for biomarker profiling used to associate agents with uncertain benefit. The report notes that therapies are placed in the uncertain benefit category when a result suggests only a decreased likelihood of response,”]).
Therefore it would be obvious for Lipsky wherein the caregivers receive clinical data of a subject and a set of treatment options for a disease or disorder of the subject, wherein the set of treatment options corresponds to clinical outcomes having future uncertainty as per the steps to Spetzler in order to determine treatment options which include levels of determined future uncertainty in order to provide patients and caregivers with a set of options to enable the optimal selection of treatment options to account for levels of certainty and uncertainty and thereby result in the optimization of treatments provided to patients.
Shrager further teaches that it was old and well known in the art before the effective filing date of the claimed invention to determine, by a trained machine learning model, a plurality of treatment features for the one or more biochemical interventions, wherein the plurality of treatment features comprises a chemical structure and a biological target of the one or more biochemical interventions, and apply a prediction module to at least clinical data of a subject and the plurality of treatment features of the one or more biochemical interventions to determine probabilistic predictions of clinical outcomes in response to the one or more biochemical interventions ([61], [62], [69], [73]-[75], [78], and [92] describe using a trained machine learning model to evaluate a plurality of potential drug treatment options for use in treating a patient based on molecule and target as well as patient clinical data; Figure 7 shows an example output of therapies)
Therefore it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Lipsky to determine, by a trained machine learning model, a plurality of treatment features for the one or more biochemical interventions, wherein the plurality of treatment features comprises a chemical structure and a biological target of the one or more biochemical interventions, and apply a prediction module to at least clinical data of a subject and the plurality of treatment features of the one or more biochemical interventions to determine probabilistic predictions of clinical outcomes in response to the one or more biochemical interventions as taught by Shrager since the claimed invention is only a combination of these old and well known elements which would have performed the same function in combination as each did separately. In the present case Lipsky already discloses a trained machine learning model and determining probabilistic predictions of outcomes for different drug treatments, and further performing the steps above taught by Shrager would yield those same functions in Lipsky, making the results predictable to one of ordinary skill in the art (MPEP 2143).
With respect to claim 107, Lipsky/Spetzler/Shrager disclose the method of claim 91. Lipsky does not expressly disclose wherein the one or more biochemical interventions comprise chemotherapy.
However, Shrager teaches that it was old and well known in the art before the effective filing date of the claimed invention to have the one or more biochemical interventions comprise chemotherapy ([61], [62], [69], [73]-[75], [78], and [92] describe using a trained machine learning model to evaluate a plurality of potential drug treatment options for use in treating a patient based on molecule and target as well as patient clinical data; Figure 7 shows an example output of therapies; [45], [62], and [75] specify chemotherapy as among the treatments)
Therefore it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of Lipsky, Spetzler, and Shrager to have the one or more biochemical interventions comprise chemotherapy as taught by Shrager since the claimed invention is only a combination of these old and well known elements which would have performed the same function in combination as each did separately. In the present case Lipsky, Spetzler, and Shrager already teach the one or more biochemical interventions, and having them include chemotherapy as taught by Shrager would yield the same function in Lipsky, Spetzler, and Shrager, making the results predictable to one of ordinary skill in the art (MPEP 2143).
With respect to claim 108, Lipsky/Spetzler/Shrager disclose the method of claim 91. Lipsky does not expressly disclose wherein the one or more biochemical interventions comprise: an alkylator, an antibiotic, an antimetabolite, a topoisomerase inhibitor, a mitosis inhibitor, a hormonal therapy, a steroid, an estrogen inhibitor, an androgen inhibitor, an LH-RH analog, an anti-aromatase agent, an immunotherapy, an interferon, an interleukin 2, a vaccine, or a combination thereof.
However, Shrager teaches that it was old and well known in the art before the effective filing date of the claimed invention to have the one or more biochemical interventions comprise: an alkylator, an antibiotic, an antimetabolite, a topoisomerase inhibitor, a mitosis inhibitor, a hormonal therapy, a steroid, an estrogen inhibitor, an androgen inhibitor, an LH-RH analog, an anti-aromatase agent, an immunotherapy, an interferon, an interleukin 2, a vaccine, or a combination thereof ([45] “a treatment option can refer to a specific treatment ( e.g., active agent and/or dosing regimen) or mode of treatment (e.g., chemotherapy, surgery). Examples of treatment options include radiation, chemotherapy (e.g., adjuvant or neo-adjuvant, using specific chemotherapeutic agents, etc.), surgery, targeted therapies (e.g., monoclonal antibody treatment), hormone therapy, stem cell transplant, and immunotherapy (e.g., using immune modulators to enhance an immune response). Examples of chemotherapeutic agents include alkylating agents, plant alkaloids, anti-metabolites, anti-microtubule agents, topoisomerase inhibitors, retinoids, ribonucleotide reductase inhibitors, adrenocortical steroid inhibitors, cytotoxic antibiotics, or other agents. Examples of targeted therapeutic agents include small molecule inhibitors such as imatinib, gefitinib, erlotinib, sorafenib, sunitinib, dasatinib, lapatinib, nilotinib, bortezomib, crizotinib, obatoclax, navitoclax, iniparib, perifosine, apatinib, vemurafenib, dabrafenib, trametinib, and V AL-083. Examples of targeted therapeutic agents also include monoclonal antibodies such as rituximab, trastuzumab, alemtuzumab, cetuximab, bevacizumab, panitumumab, and ipilimumab”)
Therefore it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of Lipsky, Spetzler, and Shrager to have the one or more biochemical interventions comprise: an alkylator, an antibiotic, an antimetabolite, a topoisomerase inhibitor, a mitosis inhibitor, a hormonal therapy, a steroid, an estrogen inhibitor, an androgen inhibitor, an LH-RH analog, an anti-aromatase agent, an immunotherapy, an interferon, an interleukin 2, a vaccine, or a combination thereofas taught by Shrager since the claimed invention is only a combination of these old and well known elements which would have performed the same function in combination as each did separately. In the present case Lipsky, Spetzler, and Shrager already teach the one or more biochemical interventions, and having them include one or more of the above biochemical interventions as taught by Shrager would yield the same function in Lipsky, Spetzler, and Shrager, making the results predictable to one of ordinary skill in the art (MPEP 2143).
Claims 89, 90, 104, and 105 are rejected under 35 U.S.C. 103 as being unpatentable over Lipsky et al (US Patent Application Publication 2021/0104321) in view of Spetzler et al (US Patent Application Publication 2020/0024669) and Shrager et al (WO 2019/144116) as applied to claims 76 and 91, and further in view of McNutt et al (US Patent Application Publication 2017/0083682).
With respect to claim 89, Lipsky/Spetzler/Shrager teach the system of claim 76.
Lipsky does not explicitly disclose, however McNutt discloses wherein the instructions are operable, when executed by the computer processor, to cause the computer processor to further generate an electronic report comprising the probabilistic predictions of clinical outcomes in response to one or more biochemical interventions of the set of treatment options, and wherein the electronic report is used to select a treatment option from among the set of treatment options based at least in part on the probabilistic predictions of clinical outcomes of the set of treatment options ([45, 46 “output device may include, e.g., but not limited to, display, and display interface, including displays, printers, speakers, cathode ray tubes (CRTs), plasma displays, light-emitting diode (LED) displays, liquid crystal displays (LCDs), printers, vacuum florescent displays (VFDs), surface-conduction electron-emitter displays (SEDs), field emission displays (FEDs),” 50 “risk evaluation may be made based on the proximity of critical structures to target volumes with all the clinical and demographic information to provide input to the automated treatment planning,” 71 “embodiment of the current invention can establish a data-mining framework in which treatment planning data and normal tissue complication effects in an integrated, analytic oncology database can be efficiently and automatically formulated into meaningful clinical recommendations,” 77-83, 304 “data integrity, tools are being developed to assist with identifying possible errant data in the system. These tools evaluate data for consistency and completeness. As with any clinical information, the data can be improperly recorded. Integrity checks offer a way to systematically look for errant data to report and correct,” Fig. 29]). Examiner Note: Examiner interprets McNutt extensive implementation of treatment plans across a wide range of situations as well as the selection of relevant features to disclose the implementation of treatment plans with respect to a wide variety of options and predictions of outcomes associated with the implementation of the treatment plans and therefore as referenced above the planning of the treatments is determined to be disclosed by McNutt.
Therefore it would be obvious for Lipsky wherein the instructions are operable, when executed by the computer processor, to cause the computer processor to further generate an electronic report comprising the probabilistic predictions of clinical outcomes in response to the one or more biochemical interventions of the set of treatment options, and wherein the electronic report is used to select a treatment option from among the set of treatment options based at least in part on the probabilistic predictions of clinical outcomes of the set of treatment options as per the steps to McNutt in order to determine treatment options which include levels of determined future uncertainty in order to provide patients and caregivers with a set of options to enable the optimal selection of treatment options to account for levels of certainty and uncertainty and thereby result in the optimization of treatments provided to patients.
With respect to claim 90, Lipsky/Spetzler/Shrager/McNutt teach the system of claim 89.
Lipsky does not explicitly disclose, however McNutt discloses wherein the selected treatment option is administered to the subject, and wherein the prediction module is further applied to outcome data of the subject that is obtained subsequent to administering the selected treatment option to the subject, to determine updated probabilistic predictions of the clinical outcomes of the set of treatment options ([308 “knowledge discovery in databases (KDD) [80]. Typically the vast majority of data analyzed was not collected for that purpose, but rather in the course of an institution conducting its general activities. In the case of health-care, data is generally from electronic health records (EHR), or other components within hospital information system,” 309 “divides KDD into nine steps: (1) understanding the problem domain and the previous work in the area; (2) selecting a target dataset; (3) data cleaning and preprocessing; (4) data reduction and projection; (5) matching the knowledge discovery goals with a data mining approach; (6) exploratory analysis with hypothesis and model testing; (7) data mining; (8) interpreting results; and (9) acting on discovered knowledge,” 340 “set of best features is selected using information gain. Complications are modeled using the following machine learning algorithms: linear regression (LR), random forest (RF) [113], and naïve Bayes (NB),” 373 “one embodiment includes a system that can demonstrate individualized medicine for cancer patients by substantially improving predictions of treatment related toxicities and enabling clinicians the ability to adjust their radiation doses or their symptom management regimens to improve care for their patients,” Fig. 29]). Examiner Note: Examiner interprets McNutt extensive implementation of treatment plans across a wide range of situations as well as the selection of relevant features to disclose the implementation of treatment plans with respect to a wide variety of options and predictions of outcomes associated with the implementation of the treatment plans and therefore as referenced above the planning of the treatments is determined to be disclosed by McNutt.
Therefore it would be obvious for Lipsky wherein the selected treatment option is administered to the subject, and wherein the prediction module is further applied to outcome data of the subject that is obtained subsequent to administering the selected treatment option to the subject, to determine updated probabilistic predictions of the clinical outcomes of the set of treatment options as per the steps to McNutt in order to determine treatment options which include levels of determined future uncertainty in order to provide patients and caregivers with a set of options to enable the optimal selection of treatment options to account for levels of certainty and uncertainty and thereby result in the optimization of treatments provided to patients.
With respect to claim 104, Lipsky/Spetzler/Shrager teach the method of claim 91.
Lipsky does not explicitly disclose, however McNutt discloses wherein the instructions are operable, when executed by the computer processor, to cause the computer processor to further generate an electronic report comprising the probabilistic predictions of clinical outcomes in response to one or more biochemical interventions of the set of treatment options, and wherein the electronic report is used to select a treatment option from among the set of treatment options based at least in part on the probabilistic predictions of clinical outcomes in response to the one or more biochemical interventions of the set of treatment options ([45, 46 “output device may include, e.g., but not limited to, display, and display interface, including displays, printers, speakers, cathode ray tubes (CRTs), plasma displays, light-emitting diode (LED) displays, liquid crystal displays (LCDs), printers, vacuum florescent displays (VFDs), surface-conduction electron-emitter displays (SEDs), field emission displays (FEDs),” 50 “risk evaluation may be made based on the proximity of critical structures to target volumes with all the clinical and demographic information to provide input to the automated treatment planning,” 71 “embodiment of the current invention can establish a data-mining framework in which treatment planning data and normal tissue complication effects in an integrated, analytic oncology database can be efficiently and automatically formulated into meaningful clinical recommendations,” 77-83, 304 “data integrity, tools are being developed to assist with identifying possible errant data in the system. These tools evaluate data for consistency and completeness. As with any clinical information, the data can be improperly recorded. Integrity checks offer a way to systematically look for errant data to report and correct,” Fig. 29]). Examiner Note: Examiner interprets McNutt extensive implementation of treatment plans across a wide range of situations as well as the selection of relevant features to disclose the implementation of treatment plans with respect to a wide variety of options and predictions of outcomes associated with the implementation of the treatment plans and therefore as referenced above the planning of the treatments is determined to be disclosed by McNutt.
Therefore it would be obvious for Lipsky wherein the instructions are operable, when executed by the computer processor, to cause the computer processor to further generate an electronic report comprising the probabilistic predictions of clinical outcomes in response to the one or more biochemical interventions of the set of treatment options, and wherein the electronic report is used to select a treatment option from among the set of treatment options based at least in part on the probabilistic predictions of clinical outcomes in response to the one or more biochemical interventions of the set of treatment options as per the steps to McNutt in order to determine treatment options which include levels of determined future uncertainty in order to provide patients and caregivers with a set of options to enable the optimal selection of treatment options to account for levels of certainty and uncertainty and thereby result in the optimization of treatments provided to patients.
Claim 105 recites limitations similar to those recited in claim 90, and is rejected on the same grounds set out above with respect to claim 90.
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 WILLIAM G LULTSCHIK whose telephone number is (571)272-3780. The examiner can normally be reached 9am - 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, Fonya Long can be reached at (571) 270-5096. 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.
/Gregory Lultschik/Examiner, Art Unit 3682
Prosecution Insights