DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Status of Claims
Claims 1-17 and 31-34 are pending. All have been examined on the merits.
Information Disclosure Statement
The information disclosure statements filed 8/13/2022, 8/30/2022 and 10/14/2022 are acknowledged. A signed copy of the corresponding 1449 form has been included with this Office action.
Priority
Priority As detailed on the 8/12/2022 filing receipt, this application claims priority to as early as 02/15/2019. At this point in examination, all claims have been interpreted as being accorded this priority date.
Specification
The disclosure is objected to because of the following informalities: The lack of spaces between words makes the text hard to follow as disclosed in pages (47-63).
Appropriate correction is required.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION. —The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claim 1 recites the limitation “needing surgery” The metes and bounds of the limitations are unclear. The specification did not define the limitation “needing surgery,” the metes and bounds of the limitation are not provided in the claims nor the specifications. One skilled in the art would not recognize the metes and bounds of “needing surgery”. Therefore, the limitation is indefinite.
Claim 1 recites the limitation “the mass spectral data” in step (a), line 2. The limitation lacks antecedent basis. Although, mass spectrometry was conducted, the recited
does not clearly recite the use of the mass spectral data.
Claims 1, 17, 31 and 33 recites the classification labels (4 categories) either high, Low, highest, and lowest. The specification discloses (page 45, table 46) a table that shows the patient characteristics by classification label, the features based on which the categories identified in the table are not clear. Considering both the claims and specification, the metes and bounds of the claims are unclear and the scoop of the claims cannot be ascertained.
Claims 2, 11, 16, 31 and 33 recites “Appendix A”, yet the claim does not specify the contents of the “Appendix A” or the table recited. The claims recited are indefinite for failing to practically point out and distinctly claim “Appendix A.” The metes and bounds of the claims are unclear and the scoop of the claims cannot be ascertained.
Claims 4, 5, 13, 14 and 16 recites a “figure”, yet the figure is not shown in the claims, which renders the claims indefinite. The metes and bounds of the claims are unclear and the scoop of the claims cannot be ascertained.
Claim 34 recites the limitation “more close follow up”. The metes and bounds of the limitation are unclear. One skilled in the art would not recognize what encompasses “more close” pertains to. The specification discloses “If and when the samples change class label from G2 to G1 then the patient could be guided to more aggressive treatment, e.g., adjuvant chemotherapy, immunotherapy, radiation therapy or more close follow-up.” (Page 60, Lines 10-11). The specification does not define or provide the metes and bounds of the limitation. Therefore, the limitation is indefinite.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-17 and 31-34 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. The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception because, the claims do not include additional elements that are sufficient to amount to significantly more than the judicial exceptions because the claims recite additional elements that are generic, conventional, or nonspecific.
Framework Analysis 0f Claims 1-17 and 31-34:
Step 1: Are the claims directed to a category of statutory subject matter (a process, machine, manufacture, or composition of matter? (See MPEP § 2106.03)
Claims 1-15 and 31-34 are properly directed to a 101 statutory category, specifically: a process: “Method”.
Claims 16 and 17 are properly directed to a 101 statutory category, specifically: a device: “programmed computer”.
[Step 1: claims 1-15, 31-34, 16 and 17: YES]
Step 2A, Prong One: Do the claims recite a judicially recognized exception, i.e., an abstract idea, a law of nature, or a natural phenomenon? (See MPEP § 2106.04(a))
Claims 1-17 and 31-34 recite abstract ideas. The MPEP at 2106.04(a)(2) further explains that abstract ideas are defined as:
• mathematical concepts, (mathematical formulas or equations, mathematical
relationships and mathematical calculations);
• certain methods of organizing human activity (fundamental economic practices
or principles, managing personal behavior or relationships or interactions between people); and/or
• mental processes (procedures for observing, evaluating, analyzing/ judging and
organizing information).
The MPEP at 2106.04(b) defines natural law/ natural phenomena as:
• naturally occurring principles/ relations that are naturally occurring or that do not have
markedly different characteristics compared to what occurs in nature.
With respect to the instant claims, under Step 2A, Prong One evaluation, the claims are found to recite abstract ideas that fall into the grouping of mathematical concepts and mental processes.
Regarding the recited in claim 1, implementing a classifier is a mathematical concept of a calculation and is an abstract idea.
Regarding the recited in claim 1, comparing the integrated intensity values obtained in step (a) with feature values of a reference set of class-labeled mass spectral data. Comparing data is a mental process and is an abstract idea.
Regarding the recited in claim 1, using hierarchical classification, is a mathematical concept of a calculation and is an abstract idea.
Regarding the recited in claim 10, performing a risk assessment of recurrence of cancer in an early stage non-small-cell lung cancer patient, is a mental process and is an abstract idea.
Regarding the recited in claim 10, performing a hierarchical classification procedure on the mass spectrometry data, using a hierarchical classification is a mathematical concept of a calculation and is an abstract idea.
Regarding the recited in claim 10, generating a classification label using a classifier, is a mathematical concept of a calculation and is an abstract idea.
Regarding the recited in claim 16, using a hierarchical classifier is a mathematical concept of a calculation and is an abstract idea.
Regarding the recited in claim 17, generating a class label using a classifier, is a mathematical concept of a calculation and is an abstract idea.
Regarding the recited in claim 31, Using a computer-based classifier and classifying the mass spectrum of the sample obtained, is a mathematical concept of a calculation and is an abstract idea.
Regarding the recited in claim 33, generates a class label using a classifier, is a mathematical concept of a calculation and is an abstract idea.
[Step 2A, Prong One, abstract idea: claims 1, 10, 16, 17, 31 and 33: YES]
Step 2A, Prong Two: If the claims recite a judicial exception under Prong One, then is the judicial exception integrated into a practical application? (See MPEP § 2106.04(d))
A claim can be said to integrate a judicial exception into a practical application when it applies, relies on, or uses the judicial exception in a manner that imposes a meaningful limit on the judicial exception.
Regarding claims 1, 10, 16, 17, 32 and 34: Additional elements have been added to the claims. Yet the claims fail to integrate the judicial exception into a practical application [see MPEP § 2106.04(d)(III)].
Claims 16 and 17 additional elements are, A programmed computer, processing unit and a memory.
The programmed computer, processing unit and a memory does not apply the mathematical processes into any practical application, rather it is simply a device for carrying out the mathematical processes, as disclosed in the specifications “Computer memory for use in conducting a classification procedure” (page 10, Lines 3-4).
The use of a computer or other machinery in its ordinary capacity for economic or other tasks (e.g., to receive, store, or transmit data) or simply adding a general-purpose computer or computer components after the fact to an abstract idea (e.g., a fundamental economic practice or mathematical equation) does not integrate a judicial exception into a practical application or provide significantly more.
Claims 1, 10, 32 and 33 additional elements are, obtain, generate and guiding treatment, Conducting spectrometry.
Providing information, such as receiving data, providing guide lines, conducting spectrometry to generate data and descriptions of data, are not considered abstract ideas, but perform functions of inputting, collecting, and outputting the data needed to carry out the abstract idea. These steps are considered insignificant extra-solution activity, and are not sufficient to integrate an abstract idea into a practical application as they do not impose
any meaningful limitation on the abstract idea or how it is performed. To integrate a judicial exception into a practical application, the additional limitations must not be mere instructions to apply the judicial exception [see MPEP § 2106.04(d) and MPEP § 2106.05(g)].
[Step 2A, 2nd prong: Claims Regarding claims 16, 17 and: NO]
Step 2B: If the claims do not integrate the judicial exception, do the claims provide an inventive concept? (See MPEP § 2106.05)
Step 2B, which evaluates whether the additional elements, individually and in combination, amount to significantly more than the judicial exception itself by providing an inventive concept. An inventive concept is furnished by an element or combination of elements that is recited in the claim in addition to the judicial exception, and is sufficient to ensure that the claim, as a whole, amounts to significantly more than the judicial exception itself (see MPEP § 2106.05).
Explaining the Berkheimer v. HP, Inc., 881 F.3d 1360, 125 USPQ2d 1649 (Fed. Cir. 2018) as an example of using the computer as a tool to perform a mental process. The MPEP stated “The patentee claimed methods for parsing and evaluating data using a computer processing system. The Federal Circuit determined that these claims were directed to mental processes of parsing and comparing data, because the steps were recited at a high level of generality and merely used computers as a tool to perform the processes. 881 F.3d at 1366, 125 USPQ2d at 1652-53”
As indicated in the summary of the Berkheimer v. HP ruling above and in view of the specifications, the claims do not include additional elements that are sufficient to amount to significantly more than the judicial exceptions because the claims recite additional elements that are generic, conventional, or nonspecific. Those additional elements are as follows:
Claims 16 and 17 additional elements are, A programmed computer, processing unit and a memory.
All elements recited are elements referred to in a generic and non-specific way in both of the claims and the specification. The specification disclosed “Computer memory for use in conducting a classification procedure” (page 10, Lines 3-4). While the method is stored in a memory medium and can be executed by the processor, together the steps do not appear to result in significantly more than a means to run a series of steps that are recited in the claims. In addition, assessing cancer risk and assessing recurrence of the tumor is well known in the art as demonstrated by Gray (Journal of Clinical Oncology, 2011).
Claims 1, 10, 32 and 33 additional elements are, obtain, generate and guiding treatment, Conducting spectrometry.
The additional elements of generating information do not cause the claims to rise to the level of significantly more than the judicial exception. The courts have recognized receiving or transmitting data over a network; storing and retrieving information in memory, and determining the level of a biomarker in blood by any means [see MPEP§2106.05(d)(II)], as well-understood, routine, conventional activity when they are claimed in a merely generic manner (e.g., at a high level of generality) or as insignificant extra-solution activity. Ocak (Proc Am Thorac Soc. 2009 Apr 15) generated data through mass spectrometry to asses NSCLC biomarkers. Thus, in light of the prior art, and MPEP § 2106.05(d)(II), the generating information steps are shown to be routine, well-understood, and conventional in the art. As a result, the additional element of data gathering steps does not provide an inventive concept by amounting to significantly more than the judicial exception.
Considering these elements alone and in combination, they do not provide an inventive concept, and do not amount to significantly more than the judicial exception itself. Thus, the additional elements do not provide an inventive concept that transforms the judicial exception into a patent eligible application of the exceptions, and the claims do not amount to significantly more that the judicial exception itself.
[Step2B: Claims 1, 10, 16, 17 and 34 NO.]
Therefore, the claims, when the limitations are considered individually and as a whole, are 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.
Claims 1and 10 are rejected under 35 U.S.C. 103(a) as being unpatentable over Markey (Proteomics 2003, 3,) in view of Ocak (Proc Am Thorac Soc. 2009 Apr 15), in view of Swan (OMICS. 2013 Dec;) in view of Gray (Journal of Clinical Oncology, 2011), Kaya (Computer Methods and Programs in Biomedicine Volume 166, November 2018), Cha (Cancer Med. 2018 Feb), Klupczynska (J Cancer Res Clin Oncol. 2017) and in view of Lynch (PLoS One. 2017 Sep 14).
Regarding the recited in claim 1, Conducting mass spectrometry on a blood-based sample obtained from the patient and obtaining integrated intensity values in the mass spectral data of a multitude of pre-determined mass-spectral features.
Markey teaches lung cancer classification using mass spectrometry “The purpose of this study was to investigate the use of a classification and regression tree (CART) model for classification of disease/nondisease clinical specimens analyzed by mass spectrometry MS.” (Page 1, Paragraph 1, Lines 1-4), In addition, Markey teaches “Decision tree classification of proteins identified by mass spectrometry of blood serum samples from people with and without lung cancer” (Title), which reads on the use of blood samples for lung cancer classification.
Markey teaches the calculation of mass to charge ratio “A classification and regression tree (CART) model was trained to classify 41 clinical specimens as disease/nondisease based on 26 variables computed from the mass to-charge ratio (m/z) and peak heights of proteins identified by mass spectroscopy.” (Abstract). The mass-to-charge ratio (m/z) in mass spectrometry data is directly related to the intensity of the detected ions. Yet Markey did not teach integrated intensity.
Markey did not mention the word features, but referred to it as variables “was trained to classify 41 clinical specimens as disease/non disease based on 26 variables computed from the mass-to-charge ratio (m/z) and peak heights of proteins identified by mass spectroscopy” (Abstract)
Regarding the recited, obtaining integrated intensity values.
Ocak teaches the use of mass spectrometry to profile lung cancer “Title” and “We will focus our discussion on how MS approaches may advance the areas of early detection, response to therapy, and prognostic evaluation.” (Abstract). Ocak teaches the use of integrated intensities to profile lung cancer “From a single raster of a section, when integrating the intensities of specific m/z signals and plotting these as a function of their spatial coordinates, hundreds of ion (or protein) images can be visualized” (Imaging Mass Spectrometry, Lines 9-11) and “Protein expression maps (or images) can be reconstructed for every m/z value detected by integrating the corresponding signal intensities and plotting these as a function of sampling coordinates.” (Under figure 3, last 3 lines)
Regarding the recited, Multitude of pre-determined mass-spectral features.
Markey used spectral data, but did not elaborate on features as pre-determined.
Swan teaches “Feature selection methods can be used prior to classification techniques, as pre-processing, to reduce the size of a dataset by selecting a subset of attributes, on which a learner is then applied” (Feature selection methods, 2nd paragraph), in addition, table.3 shows the data sets used in the research in addition to the methods used for feature selection, which reads on pre-determined features.
Regarding the recited in claim 1, Operating on the mass spectral data with a programmed computer implementing a classifier, wherein the programmed computer performs a hierarchical classification procedure on the mass spectrometry data.
Regarding, implementing a classifier.
Markey teaches the use of classifiers “A classification and regression tree (CART) model was trained to classify 41 clinical specimens as disease/nondisease based on 26 variables computed from the massto-charge ratio (m/z) and peak heights of proteins identified by mass spectroscopy.” (Abstract)
Markey did not teach hierarchical classification.
Lynch teaches classification of lung cancer patients to estimate survival “ The goal is to automatically classify lung cancer patients into groups based on clinically measurable disease-specific variables in order to estimate survival” (Abstract) and the use of hierarchical clustering “Applying Hierarchical Clustering to the SEER Lung Cancer data yields a hierarchy of cluster separations which can be visualized as the dendrogram–a common representation of these tree structures” (Hierarchical clustering).
Regarding the recited, including a first classifier (Classifier A) producing a class label in the form of high risk or low risk or the equivalent, and if the Classifier A produces the high risk label the sample is classified by a second classifier (Classifier B) generating a classification label of highest risk or high/intermediate risk or the equivalent
Markey did not teach sequential or cascade classification and the use of more than one classifier.
Kaya teaches the use of 2 classifiers, which reads on classier A and B“In this study, we proposed a cascaded classification method for malignancy classification. In the first step, nodule characteristic classifiers are trained with a base classifier. In the second step, the classification outcomes of characteristics classifiers and image features—used for training in the first step—are combined and used for malignancy classification.” ( 3.3. Experiments on cascaded classifiers)
Markey did not perform cancer risk assessment (high and low).
Regarding the recited, producing a class label in the form of high risk or low risk or the equivalent.
Mass spectrometer has been used to assess lung cancer, Ocak teaches “It supports research to identify, develop, and validate biological markers for earlier cancer detection and risk assessment.” (BIOMARKER VALIDATION AND IMPLICATIONS IN THE MANAGEMENT OF LUNG CANCER, paragraph 1 Lines 12-13).
Ocak did not specify high, intermediate, and low
Gray teaches an algorithm that calculates a recurrence score and classified patients to low, high, and intermediate risk. Gray teaches “A recurrence score (RS) and a treatment score (TS) were calculated from gene expression levels of 13 cancer-related genes” (Abstract, Patients and Method sub-section). And “Recurrence risks at 3 years were 12%, 18%, and 22% for predefined low, intermediate, and high recurrence risk groups, respectively. T stage (HR, 1.94; P < .001) and mismatch repair (MMR) status (HR, 0.31; P < .001)” (Abstract, results)
Regarding the recited in claim1, in the operating step the classifier compares the integrated intensity values obtained in step (a) with feature values of a reference set of class-labeled mass spectral data obtained from blood-based samples obtained from a multitude of other early stage non-small-cell lung cancer patients with a classification algorithm.
The recited implies the use of a training dataset based on which classification or predictions are performed. Markey teaches “ACART model [1] as implemented in SPLUS (Insightful, Seattle, WA, USA) [2] was trained to predict the classification (A = lung cancer or B = normal) ” (Page 1, 2nd paragraph , Lines 11-14). The training set reads on reference set, which is the base line or based on which predictions are made.
Regarding the recited in claim 1, detects a class label for the sample in accordance with the hierarchical classification schema relating to the risk of the cancer recurring in said patient after surgery.
Markey did not teach the risk of recurring using hierarchical models.
Mass spectrometer has been used to ass the recurrence of lung cancer, Ocak teaches “The analytical advantages of mass spectrometry (MS), including sensitivity and high-throughput, promise to make it a mainstay of novel biomarker discovery to differentiate cancer from normal cells and to predict individuals likely to develop or recur with lung cancer.” (Abstract)
Cha teaches “A hierarchical prognostic model for risk stratification in patients with early breast cancer” (Title) and Cha teaches “The CART model identified four risk layers: group 1 (SUVmax ≤6.75 and tumor size ≤2.0 cm); group 2 (SUVmax ≤6.75 and Luminal A [LumA] or TN tumor >2.0 cm); group 3 (SUVmax ≤6.75 and Luminal B [LumB] or human epidermal growth factor receptor 2 [HER2]‐enriched] tumor >2.0 cm); group 4 (SUVmax >6.75).” (Abstract)
Regarding the recited in claim 1, feature values of a reference set of class-labeled mass spectral data obtained from blood-based samples obtained from a multitude of other early stage non-small-cell lung cancer patients.
Regarding the use of reference set that is used in classification reads on a training dataset.
Regarding of the use of a training data set, Markey teaches “A classification and regression tree (CART) model was trained to classify 41 clinical specimens as disease/nondisease based on 26 variables computed from the mass-to-charge ratio (m/z) and peak heights of proteins identified by mass spectroscop” (Abstract), if a model was trained, then a training dataset was used.
Markey did not mention the word features, but referred to it as variables “was trained to classify 41 clinical specimens as disease/non disease based on 26 variables computed from the mass-to-charge ratio (m/z) and peak heights of proteins identified by mass spectroscopy” (Abstract)
Regarding the recited, obtained from a multitude of early stage non-small-cell cancer patient.
Klupczynska used data obtained from “high-resolution mass spectrometry for serum metabolite profiling of non-small-cell lung cancer (NSCLC)(Abstract, purpose). And “Only patients with early-stage disease (stages IA-IIB) were included in the study” (Abstract, methods).
Regarding the recited, Obtained from a multitude of other early stage non-small-cell lung cancer patients.
The limitation “other” is interpreted as a test or validation set.
Markey did not teach a validation or test set.
Ocak teaches “To identify patients with NSCLC who are likely to benefit from treatment with epidermal growth factor receptor (EGFR) tyrosine kinase inhibitors (TKIs), Taguchi and colleagues (94) used MALDI MS on pretreatment serum of 302 patients treated with gefitinib or erlotinib, 139 of them assigned into a training set (from three cohorts) and 163 into a validation set (from two independent cohorts)” (Blood, 6th paragraph, 1-5)
Regarding the recited, relating to the risk of the cancer recurring in said patient after surgery.
If a method assesses the recurrence of cancer, it is evident that it can be applied at any stage of the patient’s treatment timeline, including both pre and post operative settings.
Regarding claim 10
Regarding the recited in claim 10, performing mass spectrometry on a blood-based sample obtained from the patient and obtaining mass spectrometry data.
Markey teaches lung cancer classification using mass spectrometry “The purpose of this study was to investigate the use of a classification and regression tree (CART) model for classification of disease/nondisease clinical specimens analyzed by mass spectrometry MS.” (Page 1, Paragraph 1, Lines 1-4), In addition, Markey teaches “Decision tree classification of proteins identified by mass spectrometry of blood serum samples from people with and without lung cancer” (Title), which reads on the use of blood samples for lung cancer classification.
Regarding the recited, Mass spectrometry data obtained from a multitude of early stage non-small-cell cancer patient.
Klupczynska used data obtained from “high-resolution mass spectrometry for serum metabolite profiling of non-small-cell lung cancer (NSCLC)(Abstract, purpose). And “Only patients with early-stage disease (stages IA-IIB) were included in the study” (Abstract, methods)
Regarding the recited in claim 10, performing a risk assessment of recurrence of cancer in an early stage non- small-cell lung cancer patient.
Markey did not determine if the cancer is high risk or low risk. Gray teaches an algorithm that calculates a recurrence score and classified patients to low, high, and intermediate risk. Gray teaches “A recurrence score (RS) and a treatment score (TS) were calculated from gene expression levels of 13 cancer-related genes” (Abstract, Patients and Method sub-section). Gray also teaches “Recurrence risks at 3 years were 12%, 18%, and 22% for predefined low, intermediate, and high recurrence risk groups” (Abstract, results sub-section).
Regarding the recited in claim 10, performing a hierarchical classification procedure on the mass spectrometry data wherein the computing machine implements a hierarchical classifier schema including a first classifier (Classifier A) producing a class label in the form of high risk or low risk or the equivalent, and if the Classifier A produces the high risk label the sample is classified by a second classifier (Classifier B) generating a classification label of highest risk or high/intermediate risk or the equivalent, wherein if Classifier B produces the label of highest risk or the equivalent the patient is predicted to have a high risk of recurrence of the cancer following surgery.
The claim recites sequential and hierarchical classification.
Markey teaches the use of classifiers “A classification and regression tree (CART) model was trained to classify 41 clinical specimens as disease/nondisease based on 26 variables computed from the massto-charge ratio (m/z) and peak heights of proteins identified by mass spectroscopy.” (Abstract)
Markey did not teach hierarchical classification.
Lynch teaches classification of lung cancer patients to estimate survival “ The goal is to automatically classify lung cancer patients into groups based on clinically measurable disease-specific variables in order to estimate survival” (Abstract) and the use of hierarchical clustering “Applying Hierarchical Clustering to the SEER Lung Cancer data yields a hierarchy of cluster separations which can be visualized as the dendrogram–a common representation of these tree structures” (Hierarchical clustering).
Markey did not tech sequential or cascade classification and the use of more than one classifier.
Kaya teaches the use of 2 classifiers “In this study, we proposed a cascaded classification method for malignancy classification. In the first step, nodule characteristic classifiers are trained with a base classifier. In the second step, the classification outcomes of characteristics classifiers and image features—used for training in the first step—are combined and used for malignancy classification.” ( 3.3. Experiments on cascaded classifiers)
Regarding the recited, the risk of recurrence and cancer assessment (High risk and low risk).
Ocak teaches the use of mass spectrometry data in recurrence assessment, “The analytical advantages of mass spectrometry (MS), including sensitivity and high-throughput, promise to make it a mainstay of novel biomarker discovery to differentiate cancer from normal cells and to predict individuals likely to develop or recur with lung cancer.” (Abstract) and “Mass spectrometer has been used to assess lung cancer, Ocak teaches “It supports research to identify, develop, and validate biological markers for earlier cancer detection and risk assessment.” (BIOMARKER VALIDATION AND IMPLICATIONS IN THE MANAGEMENT OF LUNG CANCER, paragraph 1 Lines 12-13)
Ocak did not specify high and low risk
Gray teaches an algorithm that calculates a recurrence score and classified patients to low, high, and intermediate risk. Gray teaches “A recurrence score (RS) and a treatment score (TS) were calculated from gene expression levels of 13 cancer-related genes” (Abstract, Patients and Method sub-section). Gray also teaches “Recurrence risks at 3 years were 12%, 18%, and 22% for predefined low, intermediate, and high recurrence risk groups” (Abstract, results sub-section)
Regarding the use of hieratical classifier in risk assessment
Cha teaches “A hierarchical prognostic model for risk stratification in patients with early breast cancer” (Title) and Cha teaches “The CART model identified four risk layers: group 1 (SUVmax ≤6.75 and tumor size ≤2.0 cm); group 2 (SUVmax ≤6.75 and Luminal A [LumA] or TN tumor >2.0 cm); group 3 (SUVmax ≤6.75 and Luminal B [LumB] or human epidermal growth factor receptor 2 [HER2]‐enriched] tumor >2.0 cm); group 4 (SUVmax >6.75).” (Abstract).
It would have been obvious to a person of ordinary skill in the art to combine Markey, Ocak, Swan, Lynch, Kaya, and Gray. Mass spectrometry data has been widely used in classification tasks through machine learning techniques. Cascade or hierarchal classification involves either multiple machine learning models sequentially applied or reapplying the same method in a staged decision, making it a valid and well-established approach. Therefore, spectral data derived from mass spectrometry is well suited for cascade classification, as it benefits from the progressive refinement and feature filtering that such architecture provides. The combination would help in cancer assessment using a non-invasive method, structural decision-making guides treatment decisions, help in cancer risk treatment and provide individualized prognosis. The use of integrative intensities would improve the classification accuracy since it reflects the total molecular activity allowing for a better class separation. There is a likelihood of success, since all methods used is well known in the art before the filling date of the application. In addition, hieratical classification and expanding the feature set are widely recognized methods for enhancing model accuracy, as these techniques allow for more granular decision boundaries and better representation of complex data relations.
Claims 2 and 11 are rejected under 35 U.S.C. 103(a) as being unpatentable over Markey (Proteomics 2003, 3,) as applied to claims 1 and 10 above, in view of Ocak (Proc Am Thorac Soc. 2009 Apr 15), Kaya (Computer Methods and Programs in Biomedicine Volume 166, November 2018) and Klupczynska (J Cancer Res Clin Oncol. 2017 Apr 14).
Markey is applied to claims 1 and 10 above
Regarding claims 2 and 11
Regarding the recited in claims 2 and 11, stores a reference set of mass spectrometry data used for classification by classifiers A and B obtained from blood-based samples obtained from a multitude of early stage non-small-cell cancer patients, and wherein the mass spectrometry data includes integrated intensity values for features listed in Appendix A.
Regarding the recited, stores a reference set of mass spectrometry data used for classification,
the use of reference set that is used in classification reads on a training dataset.
Regarding the use of reference set that is used in classification reads on a training dataset.
Markey teaches “A classification and regression tree (CART) model was trained to classify 41 clinical specimens as disease/nondisease based on 26 variables computed from the mass-to-charge ratio (m/z) and peak heights of proteins identified by mass spectroscop” (Abstract), if a model was trained, then a training dataset was used.
Regarding of storing data like the reference set, Markey teaches “CART is an algorithm that learns binary decision tree representation” (Page 1, left column 2nd paragraph last 2 lines). If an algorithm is used to classify data, the data must necessary be stored in some form of memory or storage media to enable execution of the algorithm and allow access to input data during processing.
Regarding the use of 2 classifiers A and B.
Markey did not teach sequential or cascade classification and the use of more than one classifier.
Kaya teaches the use of 2 classifiers, which reads on classier A and B“In this study, we proposed a cascaded classification method for malignancy classification. In the first step, nodule characteristic classifiers are trained with a base classifier. In the second step, the classification outcomes of characteristics classifiers and image features—used for training in the first step—are combined and used for malignancy classification.” ( 3.3. Experiments on cascaded classifiers).
Regarding the recited, obtained from blood-based samples obtained from a multitude of early stage non-small-cell cancer patient.
Markey teaches lung cancer classification using mass spectrometry “The purpose of this study was to investigate the use of a classification and regression tree (CART) model for classification of disease/nondisease clinical specimens analyzed by mass spectrometry MS.” (Page 1, Paragraph 1, Lines 1-4), In addition, Markey teaches “Decision tree classification of proteins identified by mass spectrometry of blood serum samples from people with and without lung cancer” (Title), which reads on the use of blood samples for lung cancer classification.
Regarding the recited, obtained from a multitude of early stage non-small-cell cancer patient.
Klupczynska used data obtained from “high-resolution mass spectrometry for serum metabolite profiling of non-small-cell lung cancer (NSCLC)(Abstract, purpose). And “Only patients with early-stage disease (stages IA-IIB) were included in the study” (Abstract, methods)
Regarding the recited, wherein the mass spectrometry data includes integrated intensity values for features listed in Appendix A.
Ocak teaches the use of mass spectrometry to profile lung cancer “Title” and “We will focus our discussion on how MS approaches may advance the areas of early detection, response to therapy, and prognostic evaluation.” (Abstract). Ocak teaches the use of integrated intensities to profile lung cancer “From a single raster of a section, when integrating the intensities of specific m/z signals and plotting these as a function of their spatial coordinates, hundreds of ion (or protein) images can be visualized” (Imaging Mass Spectrometry, Lines 9-11) and “Protein expression maps (or images) can be reconstructed for every m/z value detected by integrating the corresponding signal intensities and plotting these as a function of sampling coordinates.” (Under figure 3, last 3 lines)
It would have been obvious to a person of ordinary skill in the art to combine Markey, Ocak, Kaya and Klupczynska teachings. The combination allows for the accurate detection and quantification of a wide range of molecules, providing a powerful tool for analyzing cancer-related biomarkers. In addition to improving accuracy of prediction and multiple classifiers can be more robust to noise and errors in the data, leading to more reliable results. There is a likelihood of success since the pre surgery scanning of a patient for early detection of cancer is well known in the art and is a routine process in the field.
Claims 3 and 12 are rejected under 35 U.S.C. 103(a) as being unpatentable over Markey (Proteomics 2003, 3,) as applied to claims 1 and 10 above, in view of Shin (PLoS One. 2015 Dec), Ocak (Proc Am Thorac Soc. 2009 Apr 15), Lynch (PLoS One. 2017 Sep 14) and Gray (Journal of Clinical Oncology, 2011).
Markey is applied to claims 1 and 10 above.
Markey is applied to claims 2 and 11 above.
Regarding claims 3 and 12
Regarding the recited in claims 3 and 12, computer implements a hierarchical classifier schema including a third classifier (Classifier C) wherein if the classifier A produces a "low risk" classification label the sample is classified by the third classifier C and wherein classifier C produces a class label of lowest risk or low/intermediate risk or the equivalent.
Regarding the recited implements a hierarchical classifier
Lynch teaches classification of lung cancer patients to estimate survival “ The goal is to automatically classify lung cancer patients into groups based on clinically measurable disease-specific variables in order to estimate survival” (Abstract) and the use of hierarchical clustering “Applying Hierarchical Clustering to the SEER Lung Cancer data yields a hierarchy of cluster separations which can be visualized as the dendrogram–a common representation of these tree structures” (Hierarchical clustering).
Regarding the use of classifier A and C and Data from classifier A is further classified by C.
Regarding the recited, Classifier C is used to classify a sample previously classified.
Shin teaches “From the individual μCs detected from the cascaded classifier, we detect clusters of μCs using two different rules.”, which also reads on the use of classifier C. (Detecting Microcalcification Clusters, Lines 1-2). Samples detected from the cascade classifier reads on data from classifier A is further classified by C.
Regarding classification of the data in to high, low, and intermediate risk
Ocak teaches the use of mass spectral data in risk assessment “It supports research to identify, develop, and validate biological markers for earlier cancer detection and risk assessment.” (BIOMARKER VALIDATION AND IMPLICATIONS IN THE MANAGEMENT OF LUNG CANCER, paragraph 1 Lines 12-13)
Gray teaches an algorithm that calculates a recurrence score and classified patients to low, high, and intermediate risk. Gray teaches “A recurrence score (RS) and a treatment score (TS) were calculated from gene expression levels of 13 cancer-related genes” (Abstract, Patients and Method sub-section). Gray also teaches “Recurrence risks at 3 years were 12%, 18%, and 22% for predefined low, intermediate, and high recurrence risk groups” (Abstract, results sub-section).
It would have been obvious to a person of ordinary skill in the art to combine Markey, Lynch, Ocak, Shin and Gray teachings. The combination would enhance the accuracy of the classification by improving modularity and flexibility. It also improves the interpretability since each decision is done in a separate node. There is a likelihood of success since hieratical classification is well known in the art and used in different fields.
Claims 4-5 and 13-14 are rejected under 35 U.S.C. 103(a) as being unpatentable over Markey (Proteomics 2003, 3,) as applied to claims 1 and 10 above, in view of Chen (arXiv:1808.04505v1 [cs.CV] 14 Aug 2018).
Markey is applied to claims 1 and 10 above.
Markey is applied to claims 2 and 11 above.
Markey is applied to claims 3 and 12 above.
Regarding claim 4 and 13
Regarding the recited in claim 4 and 13, classifiers A, B and C are combined in a four-way hierarchical schema as shown in Figure 3.
Markey did not teach hierarchical classification.
Chen teaches “For example, birds (Aves) can be categorized according to a four-level hierarchy of order” (Abstract).
Regarding claims 5 and 14
Regarding the recited in claims 5 and 14, classifiers A, B and C are combined in a three-way hierarchical schema.
Chen teaches “we investigate simultaneously predicting categories of different levels in the hierarchy and integrating this structured correlation information into the deep neural network by developing a novel Hierarchical Semantic Embedding (HSE) framework” (Abstract)
An example of a dataset used in Chen research that used three-level hierarchy is “More recently, there also released some datasets that involved categories of multiple levels, like CompCars Boxcars,
Cars-333 with three-level car categories of make, model, and year, and VegFru” (Section: 2.2 Fine-grained image datasets)
It would have been obvious to one of ordinarily skill in the art to combine Markey and Chen teachings. The combination would ensure the classification is done through structured decision tree and improved accuracy and precision. There is a likelihood of success since the hierarchical classification is well known in the art, and has been used in the field before the filling date of the application.
Claims 6 and 15 rejected under 35 U.S.C. 103(a) as being unpatentable over Markey (Proteomics 2003, 3,) as applied to claims 1 and 10 above, in view of Shin (PLoS One. 2015 Dec).
Markey is applied to claims 1 and 10 above.
Markey is applied to claims 2 and 11 above.
Markey is applied to claims 3 and 12 above.
Markey is applied to claims 4, 5 13 and 14 above.
Regarding the recited in claim 6 and 15
Regarding the recited in 6 and 15, each of the classifier’s A, B and C comprise a combination of a multitude of master classifiers each developed from a different separation of a development sample set used to generate classifiers A, B and C into training and test sets.
Regarding the recited in claim 6 and 15, combining classifiers A, B and C.
Shin teaches the use of 3 cascade classifiers, “Our framework comprises three classification stages: i) a random forest (RF) classifier for simple features capturing the second order local structure of individual μCs, where non-μC pixels in the target mammogram are efficiently eliminated; ii) a more complex discriminative restricted Boltzmann machine (DRBM) classifier for μC candidates determined in the RF stage, which automatically learns the detailed morphology of μC appearances for improved discriminative power; and iii) a detector to detect clusters of μCs from the individual μC detection results, using two different criteria.” (Abstract).
Regarding the use of training and test sets.
Markey implied the use of a training set “A classification and regression tree (CART) model was trained to classify 41 clinical specimens as disease/nondisease based on 26 variables computed from the mass-to-charge ratio (m/z) and peak heights of proteins identified by mass spectroscopy.” (Abstract), Regarding the test sets, Shin teaches “When new test data is inserted, the model computes the class label → 𝑦 by using the learned parameters.” (Figure 3).
Regarding the recited in claims 6 and 15, multitude of master classifiers each developed from a different separation of a development sample set.
Shin teaches that stage 2 classifier data is smaller subset of the data used by stage 1 which is the first classifier “The detected candidates from the stage-1 are further classified by the DRBM classifier.” (Stage-2: Discriminative Restricted Boltzmann Machine Classifier, Line 1). Same concept applied for stage 3 classifier “From the individual μCs detected from the cascaded classifier, we detect clusters of μCs using two different rules.” (Detecting Microcalcification Clusters), so each classifier is trained and tested on a different dataset, Shin teaches “Fig 4 shows the ROC and precision-recall curves for the methods in [13, 15], the stage-1 RF classifier, and the proposed cascaded classifier. For both ROC and precision-recall, a higher curve represents better performance.” (Evaluation of individual μC detection framework) (Evaluation of individual μC detection framework, 3rd paragraph) since roc curve is performed for stage 1 classifiers, it implies the use of a train and test sets for each classifier separately to be able to produce data to calculate precision and recall for each classifier.
It would have been obvious to a person of ordinary skill in the art to combine Markey and Shin. The combination would enhance the evaluation of each classifier independently and the ability of the detection and elimination of obvious negative cases, allows the optimization of each classifier separately which will improve the model’s accuracy and provides a better understanding of decision flow. The is a likelihood of success since all methods used in the combination is well known is the art before the filling date of the application.
Claim 7 is rejected under 35 U.S.C. 103(a) as being unpatentable over Markey (Proteomics 2003, 3,) as applied to claims 1 and 10 above, in view of Lewis (Published: 23 November 2010).
Markey is applied to claims 1 and 10 above.
Markey is applied to claims 2 and 11 above.
Markey is applied to claims 3 and 12 above.
Markey is applied to claims 4, 5 13 and 14 above
Markey is applied to claims 6 and 15 above.
Regarding claim 7
Regarding the recited in claim 7, the blood-based sample is obtained before surgery to treat the cancer.
Lewis teaches samples were taken just prior to bronchoscopy for suspected lung cancer. (Methods).
It would have been obvious to a person of ordinary skill in the art to combine Markey and Lewis. Preoperative samples provide a baseline for comparison with post-bronchoscopy samples, allowing for identification of changes in biomarkers related to lung health or disease. There is a likelihood of success, since cancer sample analysis before surgery, also known as pre-operative biopsy and analysis, is a well-established and widely practiced procedure
Claims 8 and 9 rejected under 35 U.S.C. 103(a) as being unpatentable over Markey (Proteomics 2003, 3,) as applied to claims 1 and 10 above, in view of Zhang (Journal of Translational Medicine, 2018).
Markey is applied to claims 1 and 10 above.
Markey is applied to claims 2 and 11 above.
Markey is applied to claims 3 and 12 above.
Markey is applied to claims 4, 5 13 and 14 above
Markey is applied to claims 6 and 15 above.
Markey is applied to claim 7 above.
Regarding claims 8 and 9
Regarding the recited in claim 8, blood samples were obtained post-surgery.
Zhang teaches “Peripheral blood was sampled within 1 week prior to surgery and post-operative samples were acquired a week after surgery” (Section methos, Patients and sample collection subsection)
Regarding the recited in claim 9, performing steps (a) and (b) on blood-based samples of the patient obtained before and after surgery to treat the cancer.
Zhang teaches “Peripheral blood was sampled within 1 week prior to surgery and post-operative samples were acquired a week after surgery” (Section methos, Patients and sample collection subsection)
It would have been obvious to a person of ordinary skill in the art to combine Markey and Zhang teachings. The combination would determine the baseline tumor activity (before surgery) and allow to monitor treatment efficacy after surgery (after surgery). There is a likelihood of success of the combination, since close monitoring of patients allows for personalized treatment adjustments, which is well known in the field and is already used in the treatment of different cancer types.
Claim 16 is rejected under 35 U.S.C. 103(a) as being unpatentable over Markey (Proteomics 2003, 3,) as applied to claims 1 and 10 above, in view of Shin (PLoS One. 2015 Dec ), Lynch (PLoS One. 2017 Sep 14), Ocak (Proc Am Thorac Soc. 2009 Apr 15), and Gray (Journal of Clinical Oncology, 2011).
Markey is applied to claims 1 and 10 above.
Markey is applied to claims 2 and 11 above.
Markey is applied to claims 3 and 12 above.
Markey is applied to claims 4, 5 13 and 14 above
Markey is applied to claims 6 and 15 above.
Markey is applied to claim 7 above.
Markey is applied to claims 8 and 9 above.
Regarding claim 16
Regarding the recited in claim 16, computer is configured as a hierarchical classifier.
Markey does not hierarchical classification.
Lynch teaches classification of lung cancer patients to estimate survival “ The goal is to automatically classify lung cancer patients into groups based on clinically measurable disease-specific variables in order to estimate survival” (Abstract) and the use of hierarchical clustering “Applying Hierarchical Clustering to the SEER Lung Cancer data yields a hierarchy of cluster separations which can be visualized as the dendrogram–a common representation of these tree structures” (Hierarchical clustering).
Regarding the recited in claim 16, combining classifiers A, B and C.
Shin teaches the use of 3 cascade classifiers “Our framework comprises three classification stages: i) a random forest (RF) classifier for simple features capturing the second order local structure of individual μCs, where non-μC pixels in the target mammogram are efficiently eliminated; ii) a more complex discriminative restricted Boltzmann machine (DRBM) classifier for μC candidates determined in the RF stage, which automatically learns the detailed morphology of μC appearances for improved discriminative power; and iii) a detector to detect clusters of μCs from the individual μC detection results, using two different criteria.” (Abstract)
Regarding the recited in claim 16, storing a reference set of mass spectral data from blood-based samples obtained from a multitude of early-stage non-small cell lung cancer patients for use in classification of the blood-based sample including feature values of the features listed in Appendix A.
Markey teaches lung cancer classification using mass spectrometry “The purpose of this study was to investigate the use of a classification and regression tree (CART) model for classification of disease/nondisease clinical specimens analyzed by mass spectrometry MS.” (Page 1, Paragraph 1, Lines 1-4), which reads on the use of spectral data in classification. In addition, Markey teaches “Decision tree classification of proteins identified by mass spectrometry of blood serum samples from people with and without lung cancer” (Title), which reads on the use of blood samples for lung cancer classification.
Regarding the use of reference set that is used in classification reads on a training dataset.
The use of a training data set, Markey teaches “A classification and regression tree (CART) model was trained to classify 41 clinical specimens as disease/nondisease based on 26 variables computed from the mass-to-charge ratio (m/z) and peak heights of proteins identified by mass spectroscop” (Abstract), if a model was trained, then a training dataset was used.
Regarding, storing data like the reference set, Markey teaches “CART is an algorithm that learns binary decision tree representation” (Page 1, left column 2nd paragraph last 2 lines). If an algorithm is used to classify data, the data must necessary be stored in some form of memory or storage media to enable execution of the algorithm and allow access to input data during processing.
Regarding the risk of recurrence of cancer
Markey did not teach risk recurrence.
Ocak teaches the use of mass spectral data in risk assessment “It supports research to identify, develop, and validate biological markers for earlier cancer detection and risk assessment.” (BIOMARKER VALIDATION AND IMPLICATIONS IN THE MANAGEMENT OF LUNG CANCER, paragraph 1 Lines 12-13)
Gray teaches an algorithm that calculates a recurrence score and classified patients to low, high, and intermediate risk. Gray teaches “A recurrence score (RS) and a treatment score (TS) were calculated from gene expression levels of 13 cancer-related genes” (Abstract, Patients and Method sub-section). Gray also teaches “Recurrence risks at 3 years were 12%, 18%, and 22% for predefined low, intermediate, and high recurrence risk groups” (Abstract, results sub-section).
Markey did not mention the word features, but referred to it as variables “was trained to classify 41 clinical specimens as disease/non disease based on 26 variables computed from the mass-to-charge ratio (m/z) and peak heights of proteins identified by mass spectroscopy” (Abstract).
It would have been obvious to a person of ordinary skill in the art to combine Markey, Lynch, Gray and Shin. The combination will increase the classification robustness and improve the classification accuracy. There is a likelihood of success since the combined methods are well known in the art before the filling date of this application and have been used in different research fields.
Claim 17 is rejected under 35 U.S.C. 103(a) as being unpatentable over Markey (Proteomics 2003, 3,) as applied to claims 1 and 10 above, in view of Shin (PLoS One. 2015 Dec), Ocak (Proc Am Thorac Soc. 2009 Apr 15), and Gray (Journal of Clinical Oncology, 2011).
Markey is applied to claims 1 and 10 above.
Markey is applied to claims 2 and 11 above.
Markey is applied to claims 3 and 12 above.
Markey is applied to claims 4, 5 13 and 14 above
Markey is applied to claims 6 and 15 above.
Markey is applied to claim 7 above.
Markey is applied to claims 8 and 9 above.
Markey is applied to claim 16.
Regarding claim 17
Regarding the recited in claim 17, Classifier A is defined by parameters such that it generates a class label of high risk or the equivalent and low risk or the equivalent; Classifier B is used to classify a sample previously classified as high risk or the equivalent by Classifier A, and is defined by parameters such that it generates a class label of highest risk or the equivalent and an intermediate classification or the equivalent; and wherein Classifier C is used to classify a sample previously classified as low risk or the equivalent by Classifier A, and is defined by parameters such that it generates a class label of lowest risk or the equivalent and an intermediate classification or the equivalent.
Regarding the use of 3 classifiers.
Shin teaches “classification stages: i) a random forest (RF) classifier “(Abstract) which reads on classifier A, the random forest classifier parameters were optimized “The optimized decisions at each node is defined by the parameters θ = (φ, τ)” (Stage-1: Random Forest Classifier with Hessian Eigenvalue Features, 4th paragraph, Line 5) and “capturing the second order local structure of individual μCs, where non-μC pixels in the target mammogram are efficiently eliminated”(Abstract) and regarding generates a class label , shin teaches the first stage classifier is used to “capturing the second order local structure of individual μCs” (Abstract).
Regarding the recited classifier B is used to classify sample previously classified.
Shin teaches “The detected candidates from the stage-1 are further classified by the DRBM classifier.” (Stage-2: Discriminative Restricted Boltzmann Machine Classifier, Line 1), the DRBM classifier reads on classifier B. Regarding the recited, is defined by parameters such that it generates a class Shin teaches “Thus, RBM is well suited for our problem of modeling the morphological ambiguity of μCs.” (Stage-2: Discriminative Restricted Boltzmann Machine Classifier, 2nd paragraph, Line 3-4), Regarding the use of parameters in DRBM, shin teaches “When new test data is inserted, the model computes the class label → 𝑦 by using the learned parameters.” (Fig 3. Restricted Boltzmann Machine.)
Regarding the recited, Classifier C is used to classify a sample previously classified, Shin teaches “From the individual μCs detected from the cascaded classifier, we detect clusters of μCs using two different rules.”, which also reads on the use of classifier C. (Detecting Microcalcification Clusters, Lines 1-2). Regarding the recited, and is defined by parameters such that it generates a class label, Shine describes the process of parameter optimization for the 3rd stage “nd previously applied to μC cluster detection by Wei et al. [15], defines a group of detected individual μCs as a true positive cluster if: 1) the distances between each pair of the μCs are less than d c1, and 2) three or more true μCs are located within some localized region A c1.” (Detecting Microcalcification Clusters, Lines 2-5).
Regarding classification of the data in to high, low, and intermediate risk.
Ocak teaches the use of mass spectral data in risk assessment “It supports research to identify, develop, and validate biological markers for earlier cancer detection and risk assessment.” (BIOMARKER VALIDATION AND IMPLICATIONS IN THE MANAGEMENT OF LUNG CANCER, paragraph 1 Lines 12-13)
Gray teaches an algorithm that calculates a recurrence score and classified patients to low, high, and intermediate risk. Gray teaches “A recurrence score (RS) and a treatment score (TS) were calculated from gene expression levels of 13 cancer-related genes” (Abstract, Patients and Method sub-section). Gray also teaches “Recurrence risks at 3 years were 12%, 18%, and 22% for predefined low, intermediate, and high recurrence risk groups” (Abstract, results sub-section)
It would have been obvious to a person of ordinary skill in the art to combine Markey, Shin, Ocak and Gray. The combination would help in cancer assessment using a non-invasive method, structural decision-making guides treatment decisions, help in cancer risk treatment and provide individualized prognosis. There is a likelihood of success, since all methods used is well known in the art before the filling date of the application. Mass spectroscopy data is commonly used in classification tasks by machine learning. Cascade classification is applying models sequentially or in stages, which is taught by this application, is well known in the art and spectral data is well suited for such architecture.
Claims 31 is rejected under 35 U.S.C. 103(a) as being unpatentable over Markey (Proteomics 2003, 3,) as applied to claims 1 and 10 above, in view of 1 and 10, in view of Zhang (Journal of Translational Medicine, 2018) , Shin (PLoS One. 2015 Dec), Ocak (Proc Am Thorac Soc. 2009 Apr 15) Klupczynska (J Cancer Res Clin Oncol. 2017) and Gray (Journal of Clinical Oncology, 2011).
Markey is applied to claims 1 and 10 above.
Markey is applied to claims 2 and 11 above.
Markey is applied to claims 3 and 12 above.
Markey is applied to claims 4, 5 13 and 14 above
Markey is applied to claims 6 and 15 above.
Markey is applied to claim 7 above.
Markey is applied to claims 8 and 9 above.
Markey is applied to claim 16.
Markey is applied to claim 17 above.
Regarding the recited in claim 31
Regarding the recited in claim 31, the blood-based sample obtained from the patient is a pre-surgery blood-based sample.
Markey did not teach pre-surgery blood-based samples obtained from other early-stage NSCLC patients.
Klupczynska used data obtained from “high-resolution mass spectrometry for serum metabolite profiling of non-small-cell lung cancer (NSCLC)(Abstract, purpose). And “Only patients with early-stage disease (stages IA-IIB) were included in the study” (Abstract, methods)
Regarding the recited in claim 31, the integrated intensity values in the mass spectral data of a multitude of pre-determined mass-spectral features are as listed in Appendix A.
Regarding the use of mass spectral data.
Markey teaches “A classification and regression tree (CART) model was trained to classify 41 clinical specimens as disease/nondisease based on 26 variables computed from the mass-to-charge ratio (m/z) and peak heights of proteins identified by mass spectroscopy.” (Abstract).
Regarding the recited, Multitude of pre-determined mass-spectral features.
Markey used spectral data, but did not elaborate on features as pre-determined.
Ocak teaches, the determination of features before classification “Statistical analyses of these data for biomarkers focus on the selection of MS features and differential expression levels between the study groups and on building class prediction models based on the selected features” (Data analysis, Lines 7-9)
Regarding the recited, integrated intensity values.
Ocak teaches the use of mass spectrometry to profile lung cancer “Title” and “We will focus our discussion on how MS approaches may advance the areas of early detection, response to therapy, and prognostic evaluation.” (Abstract). Ocak teaches the use of integrated intensities to profile lung cancer “From a single raster of a section, when integrating the intensities of specific m/z signals and plotting these as a function of their spatial coordinates, hundreds of ion (or protein) images can be visualized” (Imaging Mass Spectrometry, Lines 9-11) and “Protein expression maps (or images) can be reconstructed for every m/z value detected by integrating the corresponding signal intensities and plotting these as a function of sampling coordinates.” (Under figure 3, last 3 lines)
Regarding the recited in claim 31, the mass spectrum of the sample is classified with a computer-based classifier developed from a set of blood-based samples obtained from other early-stage NSCLC patients.
The limitation “other” is interpreted as a test or validation set.
Markey did not teach a validation or test set.
Ocak teaches “To identify patients with NSCLC who are likely to benefit from treatment with epidermal growth factor receptor (EGFR) tyrosine kinase inhibitors (TKIs), Taguchi and colleagues (94) used MALDI MS on pretreatment serum of 302 patients treated with gefitinib or erlotinib, 139 of them assigned into a training set (from three cohorts) and 163 into a validation set (from two independent cohorts)” (Blood, 6th paragraph, 1-5)
Regarding the recited in claim 31, the classifier producing a label of high or highest risk of recurrence or the equivalent and low or lowest risk of recurrence or the equivalent; (2) wherein, if the sample is not classified as high or highest risk of recurrence in accordance with the classification produced in step 1.
Shin teaches the use of 4 classifiers to reach a label, the label is not produced in stage 1 or step 1 “we present a novel cascaded classification framework for automatic detection of individual and clusters of microcalcifications (μC)” (Abstract)
Regarding the recited “producing a label of high or highest risk of recurrence or the equivalent and low or lowest risk of recurrence or the equivalent.
Mass spectrometer has been used to ass the recurrence of lung cancer, Ocak teaches “The analytical advantages of mass spectrometry (MS), including sensitivity and high-throughput, promise to make it a mainstay of novel biomarker discovery to differentiate cancer from normal cells and to predict individuals likely to develop or recur with lung cancer.” (Abstract)
Classifying the sample of high or low risk it taught by Gray. Gray teaches an algorithm that calculates a recurrence score and classified patients to low, high, and intermediate risk. Gray teaches “A recurrence score (RS) and a treatment score (TS) were calculated from gene expression levels of 13 cancer-related genes” (Abstract, Patients and Method sub-section). Gray also teaches “Recurrence risks at 3 years were 12%, 18%, and 22% for predefined low, intermediate, and high recurrence risk groups” (Abstract, results sub-section).
Regarding the recited in claim 31, obtaining a further blood-based sample from the patient after the surgery and conducting mass spectrometry on the blood-based sample including obtaining integrated intensity values of the features listed in Appendix A.
Zhang teaches “Peripheral blood was sampled within 1 week prior to surgery and post-operative samples were acquired a week after surgery” (Section methos, Patients and sample collection subsection), reads on obtaining samples after and before surgery, If a method assesses the recurrence of cancer or the risk of cancer, it is evident that it can be applied at any stage of the patient’s treatment timeline, including both pre and post operative settings.
Regarding the recited in claim 31, a computer-based classifier developed from a set of blood-based samples obtained from other early-stage NSCLC patients after surgery.
The limitation “other,” is interpreted as a validation or test set
Ocak teaches “Han and colleagues (92) used SELDI-TOF MS to analyze the serum of 253 individuals split into a training set (89 NSCLC, 68 controls) and a validation set (62 NSCLC, 34 controls)).” (Blood 5th paragraph, Lines 1-2), reads on the use of blood samples to classify patients with lung cancer “they generated a classification tree with three different protein masses that effectively identified patients with lung cancer from controls with 94% accuracy, 91% “(Blood 5th paragraph, Lines 1-2).
Regarding the recited in claim 31, the classifier generates a class label of either G1 or the equivalent or G2 or the equivalent, with G2 class label associated with a prediction that the patient will have a lower risk of recurrence as compared to risk of recurrence associated with the class label G1.
The specification discloses “are plots of time to event outcomes split on both pre-surgery
classification (Int./Lowest, labels produced by the pre-surgery classifier of Section 7) as well as post-surgery classification (G1/G2), produced by the post-surgery classifier of Section 8)” (Page 5, last 2 lines)
Markey did not link risk classification to the risk recurrence after surgery.
Gray teaches “Table 1. Analyses of Association of Single and Multiple Explanatory Variables With Risk of Recurrence in Patients Who Underwent Surgery Alone” (Table 1), which reads on generation of class label of G1 and G2.
Claim 32 is rejected under 35 U.S.C. 103(a) as being unpatentable over Markey (Proteomics 2003, 3,) as applied to claims 1 and 10 above, in view of 1 and 10, in view of Ocak (Proc Am Thorac Soc. 2009 Apr 15).
Markey is applied to claims 1 and 10 above.
Markey is applied to claims 2 and 11 above.
Markey is applied to claims 3 and 12 above.
Markey is applied to claims 4, 5 13 and 14 above
Markey is applied to claims 6 and 15 above.
Markey is applied to claim 7 above.
Markey is applied to claims 8 and 9 above.
Markey is applied to claim 16.
Markey is applied to claim 17 above.
Markey is applied to claim 31 above.
Regarding claim 32
Regarding the recited in claim 32, guiding treatment of patients based on the class label developed in 3.
Ocak teaches “To identify patients with NSCLC who are likely to benefit from treatment with epidermal growth factor receptor (EGFR) tyrosine kinase inhibitors (TKIs), Taguchi and colleagues (94) used MALDI MS on pretreatment serum of 302 patients treated with gefitinib or erlotinib, 139 of them assigned into a training set (from three cohorts) and 163 into a validation set (from two independent cohorts)” (Blood, 6th paragraph, lines 1-5). Identifying patients that will benefiting from a treatment reads on guiding treatment of patients.
It would have been obvious to a person of ordinary skill in the art to combine Markey, Ocak, Shine, Gray, Zhang and Klupczynska. The combination would offer a comprehensive cancer assessment solution by combining non-invasive methods with structural decision-making, enabling personalized treatment plans based on individual molecular activity, risk assessment, and prognosis. By utilizing integrative intensities to capture the overall molecular activity within a tumor, the classification accuracy is enhanced, leading to better patient stratification and treatment selection. There is a likelihood of success since the proposed methods leverages well-established techniques like hierarchical classification and feature expansion to further improve model accuracy and handle complex data relationships, suggesting a strong likelihood of success.
Claim 33 is rejected under 35 U.S.C. 103(a) as being unpatentable over Markey (Proteomics 2003, 3,) as applied to claims 1 and 10 above, in view of Zhang (Journal of Translational Medicine, 2018), Klupczynska (J Cancer Res Clin Oncol. 2017), Gray (Journal of Clinical Oncology, 2011) and Ocak (Proc Am Thorac Soc. 2009 Apr 15).
Markey is applied to claims 1 and 10 above.
Markey is applied to claims 2 and 11 above.
Markey is applied to claims 3 and 12 above.
Markey is applied to claims 4, 5 13 and 14 above
Markey is applied to claims 6 and 15 above.
Markey is applied to claim 7 above.
Markey is applied to claims 8 and 9 above.
Markey is applied to claim 16 above.
Markey is applied to claim 17 above.
Markey is applied to claim 31 above.
Markey is applied to claim 32 above.
Regarding claim 33
Regarding the recited in claim 33, detecting a class label in the patient.
Predicting if a patient belongs to one class of the classification, Markey teaches “A classification and regression tree (CART) model was trained to classify 41 clinical specimens as disease/nondisease based on 26 variables computed from the mass to-charge ratio (m/z) and peak heights of proteins identified by mass spectroscopy.” (Abstract).
Regarding the recited in claim 33, conducting mass spectrometry on a pre-surgery blood-based sample obtained from the patient and obtaining integrated intensity values in the mass spectral data of a multitude of pre- determined mass-spectral features shown in Appendix A.
Regarding the recited, a pre-surgery blood-based sample
Zhang teaches “For resectable gastric cancer, only one study reported that relapse-free survival was less common for patients with measurable pre-operative CTCs compared to those with non-detectable CTCs” (Section: Discussion, Lines 10-13)
Regarding the use of mass spectral data.
Markey teaches lung cancer classification using mass spectrometry “The purpose of this study was to investigate the use of a classification and regression tree (CART) model for classification of disease/non-disease clinical specimens analyzed by mass spectrometry MS.” (Page 1, Paragraph 1, Lines 1-4)Regarding using pre- determined features
Ocak teaches, the determination of features before classification “Statistical analyses of these data for biomarkers focus on the selection of MS features and differential expression levels between the study groups and on building class prediction models based on the selected features” (Data analysis, Lines 7-9)
Regarding the recited, integrated intensity values.
Ocak teaches the use of mass spectrometry to profile lung cancer “Title” and “We will focus our discussion on how MS approaches may advance the areas of early detection, response to therapy, and prognostic evaluation.” (Abstract). Ocak teaches the use of integrated intensities to profile lung cancer “From a single raster of a section, when integrating the intensities of specific m/z signals and plotting these as a function of their spatial coordinates, hundreds of ion (or protein) images can be visualized” (Imaging Mass Spectrometry, Lines 9-11) and “Protein expression maps (or images) can be reconstructed for every m/z value detected by integrating the corresponding signal intensities and plotting these as a function of sampling coordinates.” (Under figure 3, last 3 lines)
Regarding the recited in claim 33, the mass spectrum of the sample is classified with a computer-based classifier developed from a set of blood-based samples obtained from other early-stage NSCLC patients, the classifier producing a label of high or highest risk of recurrence or the equivalent and low or lowest risk of recurrence or the equivalent.
Regarding, blood samples obtained from early-stage NSCLC patients.
Klupczynska used data obtained from “high-resolution mass spectrometry for serum metabolite profiling of non-small-cell lung cancer (NSCLC)(Abstract, purpose). And “Only patients with early-stage disease (stages IA-IIB) were included in the study” (Abstract, methods)
Regarding the recited, the classifier producing a label of high or highest risk of recurrence or the equivalent and low or lowest risk of recurrence or the equivalent.
Classifying the sample of high or low risk it taught by Gray. Gray teaches an algorithm that calculates a recurrence score and classified patients to low, high, and intermediate risk. Gray teaches “A recurrence score (RS) and a treatment score (TS) were calculated from gene expression levels of 13 cancer-related genes” (Abstract, Patients and Method sub-section). Gray also teaches “Recurrence risks at 3 years were 12%, 18%, and 22% for predefined low, intermediate, and high recurrence risk groups” (Abstract, results sub-section).
Regarding the recited in claim 33, herein, if the sample is not classified as high or highest risk of recurrence in accordance with the classification produced in step (i), obtaining a further blood-based sample from the patient after the surgery and conducting mass spectrometry on the blood-based sample including obtaining integrated intensity values of the features listed in Appendix A.
Zhang teaches monitoring of patient diagnosis which suggests a resampling process “In addition to predicting patient prognosis, monitoring recurrence patterns of gastric cancer patients is vital.” (Background). In addition, Zhang teaches long term monitoring of patients (Discussion section, Line 21)
Zhang teaches “For resectable gastric cancer, only one study reported that relapse-free survival was less common for patients with measurable pre-operative CTCs compared to those with non-detectable CTCs” (Section: Discussion, Lines 10-13).
Regarding the risk of recurrence.
Gray teaches an algorithm that calculates a recurrence score and classified patients to low, high, and intermediate risk. Gray teaches “A recurrence score (RS) and a treatment score (TS) were calculated from gene expression levels of 13 cancer-related genes” (Abstract, Patients and Method sub-section). Gray also teaches “Recurrence risks at 3 years were 12%, 18%, and 22% for predefined low, intermediate, and high recurrence risk groups” (Abstract, results sub-section)
Regarding the recited in claim 33, the classifier (iii) generates a class label of either G1 or the equivalent or G2 or the equivalent, with G2 class label associated with a prediction that the patient will have a lower risk of recurrence as compared to risk of recurrence associated with the class label G1; and (B) guiding treatment of the patient based on the class label developed in step (A)(iii).
The specification discloses “are plots of time to event outcomes split on both pre-surgery
classification (Int./Lowest, labels produced by the pre-surgery classifier of Section 7) as well as post-surgery classification (G1/G2), produced by the post-surgery classifier of Section 8)” (Page 5, last 2 lines)
Markey did not link risk classification to the risk recurrence after surgery.
Gray teaches “Table 1. Analyses of Association of Single and Multiple Explanatory Variables With Risk of Recurrence in Patients Who Underwent Surgery Alone” (Table 1), which reads on generation of class label of G1 and G2.
It would have been obvious to a person of ordinary skill in the art to combine Markey, Zhang, Klupczynska, Ocak and Gray. The combination would form the foundation of a comprehensive cancer diagnosis and treatment strategy. The combination would apply risk assessment, recurrence prediction, pre and post operative monitoring based on spectroscopy classification. There is a likelihood of success since all methods are well known in the art and the combinations demonstrates multi-dimensional understanding of the tumor and treatment.
Claim 34 is rejected under 35 U.S.C. 103(a) as being unpatentable over Markey (Proteomics 2003, 3,) as applied to claims 1 and 10 above, in view of NCCN (2017) and Putten (Lung Cancer. 2001).
Markey is applied to claims 1 and 10 above.
Markey is applied to claims 2 and 11 above.
Markey is applied to claims 3 and 12 above.
Markey is applied to claims 4, 5 13 and 14 above
Markey is applied to claims 6 and 15 above.
Markey is applied to claim 7 above.
Markey is applied to claims 8 and 9 above.
Markey is applied to claim 16.
Markey is applied to claim 17 above.
Markey is applied to claim 31 above.
Markey is applied to claim 32 above.
Markey is applied to claim 33 above.
Regarding the recited in claim 34
Regarding the recited, the treatment based on the class label includes adjuvant chemotherapy, radiation therapy, immunotherapy, radiotherapy or more close follow-up and observation.
NCCN guidelines for non-small cell lung cancer version 2017, teaches “Chemotherapy Regimens”, “Radiation Therapy” (Overview, line 4), “immunotherapies” (Overview, line 13)
Putten teaches the use of radiotherapy “Eighty patients were included; median age was 57 years (range 38-77)-------. Prior treatment consisted of platinum-containing chemotherapy in 29 patients and high-dose thoracic radiotherapy in 51 patients” (Abstract). Putten teaches follow up to monitor patients and symptoms “patients with a moderate or severe symptom at baseline for whom that symptom was rated as mild or absent on two successive follow-up assessments (improvement)” (2.5.2. Palliation of symptoms and HRQL response definition).
It would have been obvious to a person of ordinary skill in the art to combine Markey, NCCN and Putten. The combination would provide non-invasive approach of diagnosis, allowing early recurrence detection based on which a tailored personalized therapy can be applied. There is a likelihood of success, since the teachings are well known in the art before the filling date of the application.
Conclusion
No claims are allowed.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MARWY ELATTAR whose telephone number is (571)272-1182. The examiner can normally be reached full time.
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, Olivia Wise can be reached on 5712722248. 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.
/M.E./Examiner, Art Unit 1685
/LARRY D RIGGS II/Supervisory Patent Examiner, Art Unit 1686
Prosecution Insights