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 .
Response to Amendment
Claims 1, 4-6, 8, 11, 13-14, and 19 have been amended.
Claims 1-20 are still pending for consideration.
Response to Arguments
Applicant’s arguments have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The text of those sections of Title 35, U.S. Code not included in this action can be found in a prior Office action.
Claims 1, 4, 6-7, and 11 are rejected under 35 U.S.C. 103 as being unpatentable over Naghavi et al. (US 20240120105 A1) in view of Kay et al. NPL “Identification of High-Risk Left-Ventricular Hypertrophy on Calcium Scoring Cardiac CT Scans: Validation in the Dallas Heart Study”.
Regarding claim 1, Naghavi et al. teaches a method, comprising: accessing computed tomography (CT) digitized imaging data stored in a memory, the CT digitized imaging data comprises computed tomography (CT) images corresponding to a patient (see para [00`3; “the method involves receiving CT scan images and storing them in a computer file; using an AI-enabled enabled volume calculator, estimating a volume of a cardiovascular structure based on the CT scan images stored in said computer file…. determining the risk of the patient for an adverse health condition”) wherein the machine learning stage is configured to generate a medical prediction of heart failure risk for the patient using the plurality of pathophysiological pathway related features (see para [0085]; “Cardiac chamber sizes and left ventricular mass measured by embodiments of the system disclosed here can facilitate predicting future AF, stroke, and HF”, see para [0076]; “CHARGE-AF is the most widely referenced epidemiological tool for prediction of AF. Similarly, BNP (brain natriuretic peptide) is the most widely used epidemiological tool for prediction of HF. Embodiments of the inventive systems and methods disclosed herein can outperform CHARGE-AF and BNP for prediction of AF and HF respectively”). However, Naghavi et al. does not teach extracting a plurality of pathophysiological pathway related features from the digitized imaging data, wherein the plurality of pathophysiological pathway related features correspond to one or more pathophysiological pathways relating to heart failure, and providing the plurality of pathophysiological pathway related features to a machine learning stage, wherein the machine learning stage is configured to generate a medical prediction of heart failure risk for the patient using the plurality of pathophysiological pathway related features
In the same field of endeavor, Kay et al. teaches extracting a plurality of pathophysiological pathway related features from the CT digitized imaging data (see Fig. 1; “(b) Radiomics extraction: the LV segmentation was used to extract radiomics features from the CT data”, see also page 1, “Method”; “extracting 107 radiomics features from the volume of interest. Four logistic regression (LR) models using different feature selection methods were built to predict high-risk LVH based on CAC-CT radiomics”), wherein the plurality of pathophysiological pathway related features correspond to one or more pathophysiological pathways relating to heart failure (see page 9, 2nd para; “identify individuals at risk for future events related to both coronary syndromes and heart failure”, see also page 14; “Automatic extraction of quantitative data from calcium scoring computed tomography (CAC-CT) can identify individuals with left ventricular hypertrophy phenotypes associated with risk for future heart failure or death”); and providing the plurality of pathophysiological pathway related features to a machine learning stage (see page 7, “Discussion”; “we devised and internally validated an end-to-end pipeline using automated segmentation, radiomic feature extraction, and machine learning to predict high-risk LVH phenotypes in a general population undergoing non-contrast CAC-CT”). Accordingly, it would have been obvious to one ordinary skill in the art of claimed invention before the effective filling date of the general use of method for facilitating determining a risk of a patient for an adverse health outcome of Neghavi et al. in view of Identification of High-Risk Left-Ventricular Hypertrophy on Calcium Scoring Cardiac CT Scans: Validation in the Dallas Heart Study of Kay et al. in order to automatically detect high-risk phenotypes of LVH in participants undergoing CAC-CT, without the need for additional imaging or radiation exposure (see Fig. 1).
Regarding claim 4, the rejection of claim 1 is incorporated herein.
Kay et al. in the combination further teaches wherein the plurality of pathophysiological pathway related features include cardiac remodeling features relating to changes in a shape, size, mass, geometry, and/or function of a heart (see page 2, 3rd para; “left ventricular hypertrophy and remodeling, can play a significant role in the identification of individuals at risk for future heart failure or death (6 10). Therefore, a screening method that could integrate the assessment of coronary calcium and left ventricular phenotypes would be highly desirable in preventive cardiac imaging. Two recent advances are critical to extracting additional information from CT scans. First, radiomics approaches can be used to extract quantitative imaging features about shape, intensity, and texture from image datasets (11)”).
Regarding claim 6, the rejection of claim 1 is incorporated herein.
Naghavi et al. in the combination further teach a plurality of machine learning models within the machine learning stage (see para [0101]; “Various machine learning and deep learning and image processing tools can be used to maximize the performance of the system”).
Kay et al. in the combination further teach further comprising: collecting clinical information from the patient (see page 3, Section 2.3; “We randomly sampled 70 participants from the DHS2 cohort. A cardiothoracic radiologist with 10 years of clinical practice manually segmented the external boundaries of the four cardiac chambers on the CAC-CT using the software 3D Slicer”); extracting a first plurality of pathophysiological pathway related features from the CT imaging data (see Fig. 1; “(b) Radiomics extraction: the LV segmentation was used to extract radiomics features from the CT data”, see also page 1, “Method”; “extracting 107 radiomics features from the volume of interest. Four logistic regression (LR) models using different feature selection methods were built to predict high-risk LVH based on CAC-CT radiomics”); utilizing the clinical information to identify specific ones of the first plurality of pathophysiological pathway related features (see page 6, Section 3.4; “One-hundred and seven radiomics features were extracted from the LV segmentation, and combined with three clinical variables that were used for the CMR-based LVH phenotyping (participant gender, BSA, and height). Figure 3 summarizes all of the features in the whole cohort”): and providing the specific ones of the first plurality of pathophysiological pathway related features to the machine learning stage as the plurality of pathophysiological pathway related features (see7, Section 4; “we devised and internally validated an end-to-end pipeline using automated segmentation, radiomic feature extraction, and machine learning to predict high-risk LVH phenotypes in a general population undergoing non-contrast CAC-CT”), see also page 9, 1st para; “emerging machine learning algorithms, such as Deep Learning, may also aid in the identification of imaging features that are beyond human interpretation”).
Regarding claim 7, the rejection of claim 1 is incorporated herein.
Naghavi et al. in the combination further teach wherein the clinical information includes one or more of obesity, diabetes, hypertension, dyslipidemia, chronic kidney disease, cardiovascular medications, and smoking status of the patient (see page 4117, right col. 1st para [0016]; “determining one or more conditions from the group consisting of…. atrial fibrillation (AF), heart failure (HF), stroke, cerebrovascular events, chronic obstructive pulmonary diseases (COPD), emphysema, dementia, ischemic heart disease, aortic aneurysm, pulmonary hypertension, cardiovascular mortality, and all-cause mortality”, and para [0018]; “the one or more health related variables is one or more of the group comprising…. medications, and other patient medical data” Note: the claim require one or more of the listed clinical information).
Regarding claim 11, the rejection of claim 1 is incorporated herein.
Naghavi et al. in the combination further teach wherein the CT digitized imaging data includes a non-contrast low-dose a computed tomography calcium scoring (CTCS) image (see para [0076]; “using cardiac CT scans (such as coronary artery calcium (CAC) scan”), see also para [0014]; “low dose lung cancer screening CT scans, and a combination of contrast enhanced and non-contrast enhanced chest CT scans”).
Claim 2, are rejected under 35 U.S.C. 103 as being unpatentable over Naghavi et al. in view of Kay et al. as applied in claim 1 above, and further in view of Szabo et al. “Radiomics of pericardial fat: a new frontier in heart failure discrimination and prediction”.
Regarding claim 2, the rejection of claim 1 is incorporated herein. The combination of Naghavi et al. and Kay et al. does not teach wherein the plurality of pathophysiological pathway related features are extracted from one or more regions of interest including one or more of heart tissue, liver tissue, adipose tissue, great artery tissue, calcifications, bone tissue, and muscle tissue.
In the same field of endeavor, Szabo et al. teach wherein the plurality of pathophysiological pathway related features are extracted from one or more regions of interest including one or more of heart tissue, liver tissue, adipose tissue, great artery tissue, calcifications, bone tissue, and muscle tissue (see page 4114, right col. 2nd para; “The aim of this study is to extend our work by performing deeper phenotyping of the pericardial adipose tissue character using radiomics analysis, to ascertain its value for classification and prediction of heart failure” Note: the claim require one or more of the listed tissue types). Accordingly, it would have been obvious to one ordinary skill in the art of claimed invention before the effective filling date of the general use of methods for facilitating determining a risk of a patient for an adverse health outcome of Neghavi et al. in view of Identification of High-Risk Left-Ventricular Hypertrophy on Calcium Scoring Cardiac CT Scans: Validation in the Dallas Heart Study of Kay et al. and Radiomics of pericardial fat: a new frontier in heart failure discrimination and prediction of Szabo et al. in order to use pericardial adipose tissue (PAT) radiomics phenotyping to differentiate existing and predict future heart failure (HF) (see page 4114, right col. 2nd para).
Claim 3 is rejected under 35 U.S.C. 103 as being unpatentable over
Naghavi et al. in view of Kay et al. as applied in claim 1 above, and further in view of Perello et al. (US 20220339171 A1).
Regarding claim 3, the rejection of claim 2 is incorporated herein. The combination of Naghavi et al. and Kay et al. does not teach wherein the calcifications include coronary calcifications and valvular calcifications.
In the same field of endeavor, Perello et al. teach wherein the calcifications include coronary calcifications and valvular calcifications (see Abstract; “preventing cardiovascular calcification, and in particular, coronary calcification, aortic artery calcification, and aortic valve calcification”). Accordingly, t would have been obvious to one ordinary skill in the art of claimed invention before the effective filling date of the general use of methods for facilitating determining a risk of a patient for an adverse health outcome of Neghavi et al. in view of Identification of High-Risk Left-Ventricular Hypertrophy on Calcium Scoring Cardiac CT Scans: Validation in the Dallas Heart Study of Kay et al. and administering a therapeutically effective amount of a compound of formula of Perello et al. in order to inhibit the progression, or preventing cardiovascular calcification in human health (see Abstract).
Claim 5 is rejected under 35 U.S.C. 103 as being unpatentable over Naghavi et al. in view of Kay et al. as applied in claim 1 above, and further in view of Pickhardt et al. NPL “Automated CT biomarkers for opportunistic prediction of future cardiovascular events and mortality in an asymptomatic screening population: a retrospective cohort study”.
Regarding claim 5, the rejection of claim 1 is incorporated herein.
Neghavi et al. et al. in the combination further teaches wherein the plurality of pathophysiological pathway related features include cardiac remodeling features, see para [0100]; “measurement of LA size, LV end diastolic size, RV end diastolic size and LV mass. Embodiments of the system can delineate the left ventricular wall, outer myocardium, and right ventricle”, see also para [0102]; “The system was used in analyses of AF and HF cumulative incidences with LA and LV volumes based top percentiles. The results show a strong predictive value for LA and LV sizes for prediction of high-risk pre-AF and pre-HF patients who are unaware of their future risk”, and para [0111]; “Image 600 shows a three-dimensional representation of the shapes and volumes of the cardiovascular structures. FIG. 7A-7B show segmentations for the aorta 705, ascending pulmonary arteries 710, descending pulmonary artery 715, right pulmonary artery 720, left pulmonary artery 725, and pulmonary trunk 730”, and para [0091]; “Accurate assessment of cardiac chamber sizes, LV mass, aortic size and calcifications, can improve cardiac risk prediction over standard risk equations”), hemodynamic features (see para [0101]; “standard CT and calcium score methods is that mid diastole, rather than end diastole is measured. For example, mid diastolic volumes can be converted to end-diastolic measurements with certain ML interpolation, with excellent accuracy”, see also para [0084]; “the system can quantify the volume of each cardiac chamber including… aorta and pulmonary artery from non-contrast CT scans”). However, the combination of Naghavi et al. and Kay et al. does not teach atherosclerosis features, visceral adiposity features, and sarcopenia features.
In the same field of endeavor, Pickhardt et al. teaches atherosclerosis features (see page 196, left col. 2nd para; “Deep-learning algorithms were used to segment and analyse the entire liver, the abdominal wall musculature, and calcified atherosclerotic aortic plaque”), visceral adiposity features, and sarcopenia features (see page 192, Abstract; “mature and fully automated CT-based algorithms with predefined metrics for quantifying aortic calcification, muscle density, ratio of visceral to subcutaneous fat, liver fat, and bone mineral density were applied to a generally healthy asymptomatic outpatient cohort of adults aged 18 years or older undergoing abdominal CT for routine colorectal cancer screening”). Accordingly, it would have been obvious to one ordinary skill in the art of claimed invention before the effective filling date of the general use of method for facilitating determining a risk of a patient for an adverse health outcome of Neghavi et al. in view of Identification of High-Risk Left-Ventricular Hypertrophy on Calcium Scoring Cardiac CT Scans: Validation in the Dallas Heart Study of Kay et al. and Automated CT biomarkers for opportunistic prediction of future cardiovascular events and mortality in an asymptomatic screening population: a retrospective cohort study of Pickhardt et al. et al. in order to investigate presymptomatic prediction of future cardiovascular events and overall survival in a healthy adult screening cohort (see page 196, left col. 2nd para).
Claim 8 is rejected under 35 U.S.C. 103 as being unpatentable over Naghavi et al. in view of Kay et al. as applied in claim 1 above, and further in view of Soni (US 20210137879 A1).
Regarding claim 8, the rejection of claim 1 is incorporated herein. The combination of Naghavi et al. and Kay et al. as a whole does not teach wherein the cardiovascular medications include one or more of statins, aspirin, betablockers, ACE inhibitors, blood pressure medications, and heart rate medications.
In the same field of endeavor, Soni et al. teach wherein the cardiovascular medications include one or more of statins, aspirin, betablockers, ACE inhibitors, blood pressure medications, and heart rate medications (see Abstract; “the present disclosure provides methods reducing the risk of cardiovascular events in a subject on statin therapy and having atrial fibrillation”, see also para [0143]; “agent administered to the subject is one or more of beta blockers….. examples of antiplatelets include aspirin”, and Table 34; “Overview of Medications …ACE Inhibitors”, and para [1127]; “blood pressure, may also provide an understanding of the effects of icosapent ethyl and potential mechanistic insight for the observed reduction in cardiovascular risk”, and para [0305]; “Among patients with cardiovascular risk factors who are receiving treatment for secondary or primary prevention, the rates of cardiovascular events remain high” and para [0445]; “Obtained vital signs (systolic and diastolic blood pressure, heart rate, respiratory rate, and body temperature)”). Accordingly, it would have been obvious to one ordinary skill in the art of claimed invention before the effective filling date of the general use of methods for facilitating determining a risk of a patient for an adverse health outcome of Neghavi et al. in view of Identification of High-Risk Left-Ventricular Hypertrophy on Calcium Scoring Cardiac CT Scans: Validation in the Dallas Heart Study of Kay et al. and methods of treating and preventing cardiovascular diseases and disorders of Soni et al.in order to reduce the risk of cardiovascular events (see Abstract).
Claims 9-10 are rejected under 35 U.S.C. 103 as being unpatentable over Naghavi et al. in view of Kay et al. as applied in claim 1 above, and further in view of Dey et al. (US 20190198178 A1).
Regarding claim 9, the rejection of claim 1 is incorporated herein.
Naghavi et al. in the combination further teach a plurality of machine learning models within the machine learning stage (see para [0101]; “Various machine learning and deep learning and image processing tools can be used to maximize the performance of the system”). However, the combination of Naghavi et al. and Kay et al. as a whole does not teach further comprising: providing the plurality of pathophysiological pathway related features to a specific machine learning model, based upon demographic information relating to the patient, wherein the plurality of machine learning models respectively have been trained to provide accurate results for a specific combination of demographic information.
In the same field of endeavor, Day et al. teach further comprising: providing the plurality of pathophysiological pathway related features to a specific machine learning model, based upon demographic information relating to the patient, wherein the plurality of machine learning models respectively have been trained to provide accurate results for a specific combination of demographic information (see para [0024]; “a personalized drug response prediction model to identify unique response patterns of each individual patient using the longitudinal patient record. In particular, the model uses separate parameters for each individual patient which represent the drug effects on an outcome of interest. The model accounts for patient heterogeneity while building predictive models for identifying drug effects”, para [0155]; “The drug response estimation engine finds specific drug responses in each patient group (block 706). The drug response estimation engine also predicts drug responses for a new individual patient”, and para [0120]; “So, in these models, both w.sub.i and α.sub.i are patient-specific”). Accordingly, it would have been obvious to one ordinary skill in the art of claimed invention before the effective filling date of the general use of methods for facilitating determining a risk of a patient for an adverse health outcome of Neghavi et al. in view of Identification of High-Risk Left-Ventricular Hypertrophy on Calcium Scoring Cardiac CT Scans: Validation in the Dallas Heart Study of Kay et al. and implement a drug response estimation engine of Dey et al. in order to provide drug response estimations or predictions (see para [0024]).
Regarding claim 10, the rejection of claim 9 is incorporated herein.
Day et al. in the combination further teach wherein the demographic information includes one or more of an age, a race, a sex, a geocode of residence, an insurance status, a diagnosis date, and a socioeconomic status of the patient (see para [0095]; “This patient information may comprise various demographic information about patients, personal contact information about patients, employment information, health insurance information, laboratory reports, physician reports from office visits, hospital charts, historical information regarding previous diagnoses, symptoms, treatments, prescription information, etc”).
Claim 12 is rejected under 35 U.S.C. 103 as being unpatentable over Naghavi et al. in view of Kay et al. as applied in claim 1 above, and further in view of Madabhushi et al. (US 20230148068 A1).
Regarding claim 12, the rejection of claim 1 is incorporated herein.
Naghavi et al. in the combination further teach further comprising: segmenting the digitized imaging data to form segmented digitized images that identify one or more of heart tissue, great artery tissue, adipose tissue, liver tissue, bone tissue, muscle tissue, and calcifications (see para [0110]; “an axial view of cardiovascular structures segmented as LA 505, LV 510, RA 515, RV 520, and LV mass 525…. FIG. 5A-5C are, respectively, axial, coronal, and sagittal views of cardiovascular structures”, see also para [0080]; “manual segmentation and delineation of one heart with attached great arteries by a well-trained radiologist or cardiologist takes about 30 minutes. However, in some embodiments of the invention disclosed here, a convolutional neural network (CNN) and a vision transformer model (such as U-Net/vision transformer) system can outperform human experts in cardiac segmentation”, and para [0111]; “FIG. 7A-7B show segmentations for the aorta 705, ascending pulmonary arteries 710, descending pulmonary artery 715, right pulmonary artery 720, left pulmonary artery 725, and pulmonary trunk 730”). However, the combination of Naghavi et al. and Kay et al. as a whole does not teach and storing the segmented digitized images in the memory as part of the digitized imaging data.
In the same field of endeavor, Madabhushi et al. teaches and storing the segmented digitized images in the memory as part of the digitized imaging data (see para [0084]; “The machine learning pipeline 206 comprises a segmentation stage 208 that is configured to segment the plurality of tiles”, see also para [0123]; “the digitized EMB images may be broken into tiles, which may be stored in the memory as intermediate digitized images 1618”). Accordingly, it would have been obvious to one ordinary skill in the art of claimed invention before the effective filling date of the general use of methods for facilitating determining a risk of a patient for an adverse health outcome of Neghavi et al. in view of Identification of High-Risk Left-Ventricular Hypertrophy on Calcium Scoring Cardiac CT Scans: Validation in the Dallas Heart Study of Kay et al. and prediction of cardiac rejection via machine learning derived features from digital endomyocardial biopsy images of Madabhushi et al. in order to generate a prediction for the patient (see para [0084).
Claim 13 is rejected under 35 U.S.C. 103 as being unpatentable over Naghavi et al. Kay et al. in view of Madabhushi et al. as applied in claims 1, and 12 above, and further in view of Wolterink et al. NPL “Graph Convolutional Networks for Coronary Artery Segmentation in Cardiac CT Angiography”.
Regarding claim 13, the rejection of claim 12 is incorporated herein. The combination of Naghavi et al., Kay et al. and Madabhushi et al. does not teach wherein the digitized imaging data is segmented using a deep learning model including a graphical neural network (GNN).
Wolterink et al. teach wherein the digitized imaging data is segmented using a deep learning model including a graph neural network (GNN) (see Abstract; “we propose to use graph convolutional networks (GCNs) to predict the spatial location of vertices in a tubular surface mesh that segments the coronary artery lumen”). Accordingly, it would have been obvious to one ordinary skill in the art of claimed invention before the effective filling date of the general use of methods for facilitating determining a risk of a patient for an adverse health outcome of Neghavi et al. in view of Identification of High-Risk Left-Ventricular Hypertrophy on Calcium Scoring Cardiac CT Scans: Validation in the Dallas Heart Study of Kay et al. and graph convolutional networks for coronary artery segmentation in cardiac CT angiography of Wolterink et al. in order to allow efficient extraction of coronary artery surface meshes (see Abstract).
Claim 14 is rejected under 35 U.S.C. 103 as being unpatentable over Naghavi et al. in view of Saalfeld et al. NPL “Prognostic role of radiomics-based body composition analysis for the 1-year survival for hepatocellular carcinoma patients”.
Regarding claim 14, Naghavi et al. teach a heart failure assessment system (see para [0029]; “a system for detecting patients at risk of developing heart failure”), comprising: a memory configured to store digitized imaging data of a patient (see para [0105]; “system 200 can include CT scan images 210, which can be stored in a computer memory, for example. CT scan images can include images obtained from CT scans”), and a machine learning stage configured to generate a medical prediction of heart failure for the patient based upon the plurality of pathophysiological pathway related features (see para [0085]; “Cardiac chamber sizes and left ventricular mass measured by embodiments of the system disclosed here can facilitate predicting future AF, stroke, and HF”, see para [0076]; “CHARGE-AF is the most widely referenced epidemiological tool for prediction of AF. Similarly, BNP (brain natriuretic peptide) is the most widely used epidemiological tool for prediction of HF. Embodiments of the inventive systems and methods disclosed herein can outperform CHARGE-AF and BNP for prediction of AF and HF respectively”). However, Naghavi et al. does not teach wherein the digitized imaging data includes two or more segmented digitized images that identify two or more of adipose tissue, bone tissue, muscle tissue, calcifications, great artery tissue, heart tissue, and liver tissue, a feature extraction tool configured to extract a plurality of pathophysiological pathway related features from the digitized imaging data, wherein the plurality of pathophysiological pathway related features comprise spatial measurements, shape radiomic features, and texture radiomic features, and wherein different combinations of the spatial measurements, the shape radiomic features, and the texture radiomic features are extracted from different ones of the two or more of the adipose tissue, the bone tissue, the muscle tissue, the calcifications, the great artery tissue, the heart tissue, and the liver tissue.
In the same field of endeavor, Saalfeld et al. teaches wherein the digitized imaging data includes two or more segmented digitized images that identify two or more of adipose tissue, bone tissue, muscle tissue, calcifications, great artery tissue, heart tissue, and liver tissue (see Abstract; “Segmentation of muscle tissue and adipose tissue was used to retrieve 881 features”, see also page 2303, left col. 1st para; “The segmentation comprised four tissue types: the SMA, which covers the musculus rectus abdominis, abdominal wall muscles, musculus psoas major, musculus quadratus lumborum and musculus erector spinae, as wellas the AT subdivided into intramuscular adipose tissue(IMAT), subcutaneous adipose tissue (SAT) and VAT” Note: the claim require two or more of the listed tissue types), a feature extraction tool configured to extract a plurality of pathophysiological pathway related features from the digitized imaging data (see page 2303, left col. last para; “We used the settings that were recommended for CT data and automatically extracted 881 features for each of the four segmented tissue types (SMA, IMAT, SAT and VAT)”), wherein the plurality of pathophysiological pathway related features comprise spatial measurements, shape radiomic features, and texture radiomic features (see page 2302, left col. 3rd para; “radiomics is a modern analysis technique that quantitatively extracts features, including shape, size, intensity and texture of analyzed tissue”) and wherein different combinations of the spatial measurements, the shape radiomic features, and the texture radiomic features are extracted from different ones of the two or more of the adipose tissue, the bone tissue, the muscle tissue, the calcifications, the great artery tissue, the heart tissue, and the liver tissue (see page 2304, right col. 4th para; “We opted for the two tissue subdivisions:1. extracting features for SMA and AT; and2. extracting features for SMA, IMAT, SAT and VAT. For example, applying a feature count of 5, this results in 10features (5 from SMA and 5 from AT) for the first option and20 features (5 from SMA, 5 from IMAT, 5 from SAT and 5from VAT) for the second option. Using the different feature counts, we obtain 5 combinations for the 2 options and the 9feature selection methods yielding a total of 90 feature sets” see also page 2302, left col. 3rd para; “radiomics is a modern analysis technique that quantitatively extracts features, including shape, size, intensity and texture of analyzed tissue”). Accordingly, it would have been obvious to one ordinary skill in the art of claimed invention before the effective filling date of the general use of method for facilitating determining a risk of a patient for an adverse health outcome of Neghavi et al. in view of Prognostic role of radiomics-based body composition analysis for the 1-year survival for hepatocellular carcinoma patients of Saalfeld et al. in order to analyse the prognostic potential of radiomics-based parameters of the skeletal musculature and adipose tissues in patients with advanced hepatocellular carcinoma (HCC) (see Abstract).
Claims 15, 17-18 are rejected under 35 U.S.C. 103 as being unpatentable over Naghavi et al. in view of Saalfeld et al. as applied in claim 14 above, and further in view of Dey et al.
Regarding claim 15, the rejection of claim 14 is incorporated herein.
Naghavi et al. in the combination further teach and wherein the machine learning stage comprises a plurality of machine learning models (see para [0101]; “Various machine learning and deep learning and image processing tools can be used to maximize the performance of the system”). The combination of Naghavi et al., and Saalfeld et al. does not teach wherein the memory is further configured to store demographic information relating to the patient, the plurality of machine learning models respectively trained to generate the medical prediction of heart failure for a specific set of demographic information; and wherein the plurality of pathophysiological pathway related features are provided to one of the plurality of machine learning models depending upon the demographic information.
Dey et al. in the combination further teach wherein the memory is further configured to store demographic information relating to the patient (see para [0095]; “The patient EMRs 322 store various information about individual patients, such as patient 302, in a manner (structured, unstructured, or a mix of structured and unstructured formats) that the information may be retrieved and processed by the healthcare cognitive system 300. This patient information may comprise various demographic information about patients, personal contact information about patients, employment information, health insurance information, laboratory reports, physician reports from office visits, hospital charts, historical information regarding previous diagnoses, symptoms, treatments, prescription information, etc”); the plurality of machine learning models respectively trained to generate the medical prediction of heart failure for a specific set of demographic information; and wherein the plurality of pathophysiological pathway related features are provided to one of the plurality of machine learning models depending upon the demographic information (see para [0024]; “a personalized drug response prediction model to identify unique response patterns of each individual patient using the longitudinal patient record. In particular, the model uses separate parameters for each individual patient which represent the drug effects on an outcome of interest. The model accounts for patient heterogeneity while building predictive models for identifying drug effects”, para [0155]; “The drug response estimation engine finds specific drug responses in each patient group (block 706). The drug response estimation engine also predicts drug responses for a new individual patient”, and para [0120]; “So, in these models, both w.sub.i and α.sub.i are patient-specific”). Accordingly, it would have been obvious to one ordinary skill in the art of claimed invention before the effective filling date of the general use of method for facilitating determining a risk of a patient for an adverse health outcome of Neghavi et al. in view of Prognostic role of radiomics-based body composition analysis for the 1-year survival for hepatocellular carcinoma patients of Saalfeld et al. and implement a drug response estimation engine of Dey et al. in order to provide drug response estimations or predictions (see para [0095]).
Regarding claim 17, the rejection of claim 14 is incorporated herein.
Naghavi et al. in the combination further teach and wherein the machine learning stage comprises a plurality of machine learning model (see para [0101]; “Various machine learning and deep learning and image processing tools can be used to maximize the performance of the system”).
Dey et al. in the combination further teach wherein the memory is further configured to store clinical information relating to the patient (see para [0095]; “the patient EMRs 322 is a patient information repository that collects patient data from a variety of sources, e.g., hospitals, laboratories, physicians' offices, health insurance companies, pharmacies, etc. The patient EMRs 322 store various information about individual patients, such as patient 302, in a manner (structured, unstructured, or a mix of structured and unstructured formats) that the information may be retrieved and processed by the healthcare cognitive system 300”); the plurality of machine learning models respectively trained to generate the medical prediction relating to heart failure for a specific set of clinical information; and wherein the plurality of pathophysiological pathway related features are provided to one of the plurality of machine learning models depending upon the clinical information (see para [0024]; “a personalized drug response prediction model to identify unique response patterns of each individual patient using the longitudinal patient record. In particular, the model uses separate parameters for each individual patient which represent the drug effects on an outcome of interest. The model accounts for patient heterogeneity while building predictive models for identifying drug effects”, para [0155]; “The drug response estimation engine finds specific drug responses in each patient group (block 706). The drug response estimation engine also predicts drug responses for a new individual patient”, and para [0120]; “So, in these models, both w.sub.i and α.sub.i are patient-specific”). Accordingly, it would have been obvious to one ordinary skill in the art of claimed invention before the effective filling date of the general use of method for facilitating determining a risk of a patient for an adverse health outcome of Neghavi et al. in view of Prognostic role of radiomics-based body composition analysis for the 1-year survival for hepatocellular carcinoma patients of Saalfeld et al. and implement a drug response estimation engine of Dey et al. in order to provide drug response estimations or predictions (see para [0095]).
Regarding claim 18, the rejection of claim 17 is incorporated herein.
Naghavi et al. in the combination further teach wherein the clinical information includes one or more of systolic blood pressure, diastolic blood pressure, chronic kidney disease, smoking status, hypertension treatment, serum cholesterol, cardiovascular risk factors, cardiovascular medications, and body mass index (see para [0008]; “It is known to calculate a CHARGE-AF score: …systolic blood pressure (20 mm Hg increments)−0.101×diastolic blood pressure (10 mm Hg increments)+0.359×current smoker+0.349×antihypertensive medication+0.237×diabetes+0.701×congestive heart failure+0.496×myocardial infarction”, see also para [0018]; “blood pressure, heart rate, blood oxygenation, blood tests, medications, and other patient medical data” and para [0106]; “the risk is determined based on the estimated volume and taking into account other variables, such as.. body mass”).
Claim 16 is rejected under 35 U.S.C. 103 as being unpatentable over Naghavi et al. in view of Saalfeld et al. as applied in claim 14 above, and further in view of Cotter et al. (US 20110119078 A1).
Regarding claim 16, the rejection of claim 14 is incorporated herein. The combination of Naghavi et al., and Saalfeld et al. does not teach wherein the medical prediction of heart failure includes a time to heart failure.
In the same field of endeavor, Cotter et al. teaches wherein the medical prediction of heart failure includes a time to heart failure (see para [0012]; “The risk of acute heart failure is computed using the algorithm and the captured data from a plurality of the defined intervals. A survival function outcome for the subject is then predicted using the output of the algorithm”, see also para [0031]; “The algorithm is configured to assess a risk of acute heart failure”). Accordingly, it would have been obvious to one ordinary skill in the art of claimed invention before the effective filling date of the general use of methods for facilitating determining a risk of a patient for an adverse health outcome of Neghavi et al. in view of Prognostic role of radiomics-based body composition analysis for the 1-year survival for hepatocellular carcinoma patients of Saalfeld et al. and a method for monitoring a health status of a human subject of Cotter et al. in order to predict a risk of heart failure in a patient or drug candidate (see para [0012]).
Claim 19 is rejected under 35 U.S.C. 103 as being unpatentable over Naghavi et al. in view of Szabo et al. and further in view of Pickhardt et al.
Regarding claim 19, Naghavi et al. teaches a non-transitory computer-readable medium storing computer-executable instructions that, when executed, cause a processor to perform operations (see also para [0150]; “The computer readable storage medium can be a tangible device that can retain and store instructions for use by an instruction execution device”), comprising: accessing digitized imaging data stored in a memory, wherein the digitized imaging data comprises a digitized image corresponding to a patient (see para [0003]; “the method involves receiving CT scan images and storing them in a computer file; using an AI-enabled enabled volume calculator, estimating a volume of a cardiovascular structure based on the CT scan images stored in said computer file…. determining the risk of the patient for an adverse health condition), wherein the plurality of pathophysiological pathway related features include cardiac remodeling features (see para [0100]; “measurement of LA size, LV end diastolic size, RV end diastolic size and LV mass. Embodiments of the system can delineate the left ventricular wall, outer myocardium, and right ventricle”, see also para [0102]; “The system was used in analyses of AF and HF cumulative incidences with LA and LV volumes based top percentiles. The results show a strong predictive value for LA and LV sizes for prediction of high-risk pre-AF and pre-HF patients who are unaware of their future risk”, and para [0111]; “Image 600 shows a three-dimensional representation of the shapes and volumes of the cardiovascular structures. FIG. 7A-7B show segmentations for the aorta 705, ascending pulmonary arteries 710, descending pulmonary artery 715, right pulmonary artery 720, left pulmonary artery 725, and pulmonary trunk 730”, and para [0091]; “Accurate assessment of cardiac chamber sizes, LV mass, aortic size and calcifications, can improve cardiac risk prediction over standard risk equations”), hemodynamic features (see para [0101]; “standard CT and calcium score methods is that mid diastole, rather than end diastole is measured. For example, mid diastolic volumes can be converted to end-diastolic measurements with certain ML interpolation, with excellent accuracy”, see also para [0084]; “the system can quantify the volume of each cardiac chamber including… aorta and pulmonary artery from non-contrast CT scans”). However, Naghavi et al. does not teach. extracting a plurality of pathophysiological pathway related features from the digitized imaging data, atherosclerosis feature, adiposity features, and sarcopenia features and providing the plurality of pathophysiological pathway related features to a machine learning stage that has been trained to generate a medical prediction of heart failure risk for the patient.
In the same field of endeavor, Szabo et al. teaches extracting a plurality of pathophysiological pathway related features from the digitized imaging data (see Abstract; “PyRadiomics was utilised to extract 104 radiomics features” see also page 4116, left col. 4th para; “using the automated pipeline described above to derive our regions of interest (ROI) for radiomics analysis”, and page 4118, Discussion”: “we set up a pipeline using radiomics feature extraction”), and providing the plurality of pathophysiological pathway related features to a machine learning stage that has been trained to generate a medical prediction of heart failure risk for the patient (see page 4119, “Discussion”; “we set up a pipeline using radiomics feature extraction and machine learning to predict high-risk PAT phenotypes .. We demonstrate for the first time that PAT radiomics can be used to discriminate prevalent HF cases ”, and see page 4122, “Conclusion”; “Machine learning classifiers built upon radiomics features depicting the amount (larger PAT diameters) and texture character (greater tissue heterogeneity) of pericardial fat can be used to discriminate individuals with prevalent heart failure and predict incidence of future heart failure”). Accordingly, it would have been obvious to one ordinary skill in the art of claimed invention before the effective filling date of the general use of method for facilitating determining a risk of a patient for an adverse health outcome of Neghavi et al. in view of Radiomics of pericardial fat: a new frontier in heart failure discrimination and prediction of Szabo et al. in order to generate good discriminative performance individuals with prevalent HF and incidence of future HF (see Abstract). However, the combination of Naghavi and Szabo et al. does not teach atherosclerosis features, visceral adiposity features, and sarcopenia features.
In the same field of endeavor, Pickhardt et al. teaches atherosclerosis features (see page 196, left col. 2nd para; “Deep-learning algorithms were used to segment and analyse the entire liver, the abdominal wall musculature, and calcified atherosclerotic aortic plaque”), visceral adiposity features, and sarcopenia features (see page 192, Abstract; “mature and fully automated CT-based algorithms with predefined metrics for quantifying aortic calcification, muscle density, ratio of visceral to subcutaneous fat, liver fat, and bone mineral density were applied to a generally healthy asymptomatic outpatient cohort of adults aged 18 years or older undergoing abdominal CT for routine colorectal cancer screening”). Accordingly, it would have been obvious to one ordinary skill in the art of claimed invention before the effective filling date of the general use of method for facilitating determining a risk of a patient for an adverse health outcome of Neghavi et al. in view of Radiomics of pericardial fat: a new frontier in heart failure discrimination and prediction of Szabo et al. and Automated CT biomarkers for opportunistic prediction of future cardiovascular events and mortality in an asymptomatic screening population: a retrospective cohort study of Pickhardt et al. et al. in order to investigate presymptomatic prediction of future cardiovascular events and overall survival in a healthy adult screening cohort (see page 196, left col. 2nd para).
Claim 20 is rejected under 35 U.S.C. 103 as being unpatentable over Naghavi et al. and Szabo et al. in view of Pickhardt et al. as applied in claim 19, above and further in view of Dey et al.
Regarding claim 20, the rejection of claim 19 is incorporated herein.
Szabo et al. in the combination further teach and providing the plurality of pathophysiological pathway related features to a specific machine learning model within the machine learning stage, based upon the demographic information relating to the patient (see page 4123, “Limitation”; “While our models used a range of radiomics features and demographic variables”). However, the sombination of Naghavi et al., Szabo et al. and Pickhardt et al. does not teach wherein the operations further comprise: storing demographic information relating to the patient in the memory.
In the same field of endeavor, Dey et al. teach wherein the operations further comprise: storing demographic information relating to the patient in the memory (see para [0095]; “The patient EMRs 322 store various information about individual patients, such as patient 302, in a manner (structured, unstructured, or a mix of structured and unstructured formats) that the information may be retrieved and processed by the healthcare cognitive system 300. This patient information may comprise various demographic information about patients, personal contact information about patients, employment information, health insurance information, laboratory reports, physician reports from office visits, hospital charts, historical information regarding previous diagnoses, symptoms, treatments, prescription information, etc”). Accordingly, it would have been obvious to one ordinary skill in the art of claimed invention before the effective filling date of the general use of methods for facilitating determining a risk of a patient for an adverse health outcome of Neghavi et al. in view of Radiomics of pericardial fat: a new frontier in heart failure discrimination and prediction of Szabo et al. and implement a drug response estimation engine of Dey et al. in order to provide drug response estimations or predictions (see para [0095]).
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 WINTA GEBRESLASSIE whose telephone number is (571)272-3475. The examiner can normally be reached Monday-Friday9:00-5:00.
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, Andrew Bee can be reached at 571-270-5180. 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.
/WINTA GEBRESLASSIE/Examiner, Art Unit 2677
Prosecution Insights