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 .
Double Patenting
The nonstatutory double patenting rejection is based on a judicially created doctrine grounded in public policy (a policy reflected in the statute) so as to prevent the unjustified or improper timewise extension of the “right to exclude” granted by a patent and to prevent possible harassment by multiple assignees. A nonstatutory double patenting rejection is appropriate where the conflicting claims are not identical, but at least one examined application claim is not patentably distinct from the reference claim(s) because the examined application claim is either anticipated by, or would have been obvious over, the reference claim(s). See, e.g., In re Berg, 140 F.3d 1428, 46 USPQ2d 1226 (Fed. Cir. 1998); In re Goodman, 11 F.3d 1046, 29 USPQ2d 2010 (Fed. Cir. 1993); In re Longi, 759 F.2d 887, 225 USPQ 645 (Fed. Cir. 1985); In re Van Ornum, 686 F.2d 937, 214 USPQ 761 (CCPA 1982); In re Vogel, 422 F.2d 438, 164 USPQ 619 (CCPA 1970); In re Thorington, 418 F.2d 528, 163 USPQ 644 (CCPA 1969).
A timely filed terminal disclaimer in compliance with 37 CFR 1.321(c) or 1.321(d) may be used to overcome an actual or provisional rejection based on nonstatutory double patenting provided the reference application or patent either is shown to be commonly owned with the examined application, or claims an invention made as a result of activities undertaken within the scope of a joint research agreement. See MPEP § 717.02 for applications subject to examination under the first inventor to file provisions of the AIA as explained in MPEP § 2159. See MPEP § 2146 et seq. for applications not subject to examination under the first inventor to file provisions of the AIA . A terminal disclaimer must be signed in compliance with 37 CFR 1.321(b).
The filing of a terminal disclaimer by itself is not a complete reply to a nonstatutory double patenting (NSDP) rejection. A complete reply requires that the terminal disclaimer be accompanied by a reply requesting reconsideration of the prior Office action. Even where the NSDP rejection is provisional the reply must be complete. See MPEP § 804, subsection I.B.1. For a reply to a non-final Office action, see 37 CFR 1.111(a). For a reply to final Office action, see 37 CFR 1.113(c). A request for reconsideration while not provided for in 37 CFR 1.113(c) may be filed after final for consideration. See MPEP §§ 706.07(e) and 714.13.
The USPTO Internet website contains terminal disclaimer forms which may be used. Please visit www.uspto.gov/patent/patents-forms. The actual filing date of the application in which the form is filed determines what form (e.g., PTO/SB/25, PTO/SB/26, PTO/AIA /25, or PTO/AIA /26) should be used. A web-based eTerminal Disclaimer may be filled out completely online using web-screens. An eTerminal Disclaimer that meets all requirements is auto-processed and approved immediately upon submission. For more information about eTerminal Disclaimers, refer to www.uspto.gov/patents/apply/applying-online/eterminal-disclaimer.
Claim 1-2, 4, 11-12, and 14 are rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1, 4, 11, 16 of U.S. Patent No. 12121327 (hereafter known as Pat ‘327). Although the claims at issue are not identical, they are not patentably distinct from each other because Pat ‘327 anticipates all the limitations as outlined in the table directly the rejection to this claim.
Claim in this application
Where the claim can be found in Pat ‘327
Further clarification (if needed)
Claims 1 and 11
See claims 1 and 4 (for claim 1 of this application) and claims 11 and 16 (for claim 11 of this application)
Claims 2 and 12
See claims 1 and 11
“iteratively trained machine learning model” implies training as claimed
Claims 4 and 14
See claims 1 and 11
Claims 1-2, 6, 10-12, 16 and 20 are rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1, 3-4, 10 and 12-13 of U.S. Patent No. 12201404 (hereafter known as Pat ‘404). Although the claims at issue are not identical, they are not patentably distinct from each other because these claims are anticipated as outlined in the table below.
Claim in this application
Where the claim can be found in Pat ‘404
Further clarification (if needed)
Claims 1 and 11
See claims 1 and 10
Claims 2 and 12
See claims 1 and 10
“iteratively trained machine learning model” implies training as claimed
Claims 6 and 16
See claims 1 and 10
Claims 10 and 20
See claims 3-4 (for claim 10) and claims 12-13 (for claim 20)
Claims 4 and 14 are rejected on the ground of nonstatutory double patenting as being unpatentable over claims 8 and 17 of Pat ‘404. Although the claims at issue are not identical, they are not patentably distinct from each other because these claims are obviated as outlined below.
Claims 8 and 17 of Pat ‘404 discloses the invention substantially as claimed including a convolution neural network which is understood to have at least one convolution layer
However, claims 8 and 17 of Pat ‘404 fail to disclose that the convolution neural network has a “plurality of convolution layers”.
It would have been obvious to one having ordinary skill in the art at the time the invention was filed to modify Pat ‘404 by including a plurality of layers because such a modification is a mere duplication of parts which has been deemed to be an obvious modification [see In re Harza, 274 F.2d 669, 124 USPQ 378 (CCPA 1960)].
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.
Claims 6 and 16 rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claims 6 and 16 recite the limitation "the selected patient characteristic" in the limitation “wherein selecting the machine-learning model form a plurality of machine-learning models is a function of the selected patient characteristic. There is insufficient antecedent basis for this limitation in the claim.
Claims 6 and 16 only dependent from claims 1-2 and 11-12 which fail to recite “a selected patient characteristic”. However, claims 3 and 13 do recite “a selected patient characteristic”. This raises questions as to interpretation of claims 6 and 16. For this examination, the interpretation taken is that claims 3 and 13 are supposed to be dependent on claims 2 and 12 respectively. Regardless if this is applicant’s intended interpretation or not, claims 6 and 16 need to be amended to clarify what is being claimed here.
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 factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claim(s) 1-2, 4, 8-12, 14 and 18-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Radzievsky et al (US 20110021933) hereafter known as Radzievsky in view of Bhushan et al (US 20170347899) hereafter known as Bhushan.
Independent claim:
Claim 1:
Radzievsky discloses:
A method [see abstract… “A method and system are presented for use in monitoring a subject's heart conditions such as ejection fraction and cardiac synchrony.”], comprising:
receiving, by a system of one or more computers [see Fig. 5 element 100 (i.e. interpreted to be at least a system of one or more computers and para 45… “as shown in FIG. 5 by a way of block diagram, a monitoring system, generally designated 100, comprises as a computer system, including inter alia a processor 112 and a data presentation utility 114 (e.g. display)” and “Monitoring system 100 preferably also includes a controller 20 associated with acoustic unit 18 for selecting acoustic receivers (microphones) to be operated during the measurement session or the measured signals of which are to be included in the acoustic measured data portion for further processing.” And para 54… “the monitoring system 100 preferably includes controller 20 configured for selecting appropriate acoustic data. Controller 20 may be associated with the acoustic unit or with a memory utility of the monitoring system where measured acoustic data is stored, and may thus operate to selected acoustic receivers to be operated during the measurement session”], electrocardiogram (ECG) data that describes at least an ECG of a first subject over a period of time [see Fig. 5 and para 45… “First and second measured data portions MD.sub.1 and MD.sub.2, produced by the ECG and acoustic measurement units 16 and 18, respectively, are input to the monitoring system 100.”];
processing, by the system, the ECG data to generate a predictive input, wherein the predictive input comprises a plurality of morphological features of the ECG data [see para 62… “Thus, the present invention provides novel techniques for monitoring various parameters characterizing the heart condition. The ejection fraction parameter can be determined from a relation (time shift) between the respective signal peaks (QRS-complexes) in the ECG signals measured on planar and diagonal electrode pairs.” Ejection fraction parameter is a being determined is a prediction and QRS complexes are morphological features of ECG];
providing, for output, the subject structural heart disease prediction for the first subject [see para 35… “Upon identifying the time shift, the system generates and displays output data indicative of the ejection fraction condition for the patient.”]
However, Radzievsky fails to disclose the steps of: “selecting a machine-learning model from a plurality of machine-learning models as a function of a patient characteristic”, “providing, by the system, the predictive input to a machine-learning model” or “processing the predictive input with the machine-learning model, wherein processing the predictive input with the machine-learning model comprises generating a subject structural heart disease prediction for the first subject”.
Bhushan discloses in the analogous art of cardiovascular diagnostics [see abstract… “The various embodiments of the present invention provide a system and method for a fully mobile, non-invasive, continuous system for monitoring the cardiovascular health of an individual.”] combining information from multiple sensors including ECG data with a machine learning algorithm selected from a choice of multiple different algorithms (including that of convolutional neural networks and/or Bayesian Classifiers and/or support vector machines) that is trained on data to output data related to ejection fractions (i.e. structural heart disease prediction) to provide customized alerts to a user [see para 44… “In various embodiments, the data stored on the web for multiple Users, is used in Machine learning algorithms such as a convolutional neural networks and/or Bayesian Classifiers and/or support vector machines, to distinguish between healthy and pathological conditions of the User in question, by using the stored and annotated data as a training set, and applying the classification algorithms on the User's data.” And see para 47… “Further, the system combines subjective information and information from multiple sensors on multiple users, as described above, to run Machine Learning algorithms, Bayesian classifiers or other kinds of training and testing protocols, in order to provide alerts that are customized for each individual, based on the normal parameters for the users in the same demographic section.” And para 56… “the Biostrip device uses data from the ECG sensor, PPG sensor, and the SCG as measured from the accelerometer, as described herein, and when the Biostrip device is affixed on some part of the chest, to calculate values for the cardiac time intervals (CTIs) including, but not limited to: Pre-ejection period (PEP), left ventricular ejection time (LVET)”].
It would have been obvious to one having ordinary skill in the art at that time the invention was filed to modify Radzievsky to choice and use a machine-learning model (i.e. selecting a machine-learning model form a plurality of machine-learning models), input the sensor data (i.e. providing the predictive input) to obtain output related ejection fractions similarly to that disclosed by Bhushan to provide an alert customized to a user about a user’s cardiovascular health.
Independent claim:
Claim 11:
A system [see abstract… “A method and system are presented for use in monitoring a subject's heart conditions such as ejection fraction and cardiac synchrony.”] of one or more computers [see Fig. 5 element 100 (i.e. interpreted to be at least a system of one or more computers) and para 45… “as shown in FIG. 5 by a way of block diagram, a monitoring system, generally designated 100, comprises as a computer system, including inter alia a processor 112 and a data presentation utility 114 (e.g. display)” and “Monitoring system 100 preferably also includes a controller 20 associated with acoustic unit 18 for selecting acoustic receivers (microphones) to be operated during the measurement session or the measured signals of which are to be included in the acoustic measured data portion for further processing.”] comprising at least a processor and a memory encoded with instructions that, when executed by the at least a processor of the system [see Fig. 5 element 112 (i.e. processor) and element 20 and para 54… “Controller 20 may be associated with the acoustic unit or with a memory utility of the monitoring system where measured acoustic data is stored”], cause the system to perform operations comprising:
receiving electrocardiogram (ECG) data that describes at least an ECG of a first subject over a period of time [see Fig. 5 and para 45… “First and second measured data portions MD.sub.1 and MD.sub.2, produced by the ECG and acoustic measurement units 16 and 18, respectively, are input to the monitoring system 100.”];
processing the ECG data to generate a predictive input, wherein the predictive input comprises a plurality of morphological features of the ECG data [para 62… “Thus, the present invention provides novel techniques for monitoring various parameters characterizing the heart condition. The ejection fraction parameter can be determined from a relation (time shift) between the respective signal peaks (QRS-complexes) in the ECG signals measured on planar and diagonal electrode pairs.” Ejection fraction parameter is a being determined is a prediction and QRS complexes are morphological features of ECG];
providing, for output, the subject structural heart disease prediction for the first subject [see para 35… “Upon identifying the time shift, the system generates and displays output data indicative of the ejection fraction condition for the patient.”].
However, Radzievsky fails to disclose the processor as causing the system to perform operations of “selecting a machine-learning model from a plurality of machine-learning models as a function of a patient characteristic”. “providing the predictive input to a machine-learning model”, or “processing the predictive input with the machine-learning model, wherein processing the predictive input with the machine-learning model comprises generating a subject structural heart disease prediction for the first subject” as claimed.
Bhushan discloses in the analogous art of cardiovascular diagnostics [see abstract… “The various embodiments of the present invention provide a system and method for a fully mobile, non-invasive, continuous system for monitoring the cardiovascular health of an individual.”] combining information from multiple sensors including ECG data with a machine learning algorithm selected from a choice of multiple different algorithms (including that of convolutional neural networks and/or Bayesian Classifiers and/or support vector machines) that is trained on data to output data related to ejection fractions (i.e. structural heart disease prediction) to provide customized alerts to a user [see para 44… “In various embodiments, the data stored on the web for multiple Users, is used in Machine learning algorithms such as a convolutional neural networks and/or Bayesian Classifiers and/or support vector machines, to distinguish between healthy and pathological conditions of the User in question, by using the stored and annotated data as a training set, and applying the classification algorithms on the User's data.” And see para 47… “Further, the system combines subjective information and information from multiple sensors on multiple users, as described above, to run Machine Learning algorithms, Bayesian classifiers or other kinds of training and testing protocols, in order to provide alerts that are customized for each individual, based on the normal parameters for the users in the same demographic section.” And para 56… “the Biostrip device uses data from the ECG sensor, PPG sensor, and the SCG as measured from the accelerometer, as described herein, and when the Biostrip device is affixed on some part of the chest, to calculate values for the cardiac time intervals (CTIs) including, but not limited to: Pre-ejection period (PEP), left ventricular ejection time (LVET)”].
It would have been obvious to one having ordinary skill in the art at that time the invention was filed to modify Radzievsky’s processor to choose and use a machine-learning model (i.e. selecting a machine-learning model form a plurality of machine-learning models), input the sensor data (i.e. providing the predictive input) to obtain output related ejection fractions similarly to that disclosed by Bhushan to provide an alert customized to a user about a user’s cardiovascular health.
Dependent claims:
Regarding claims 2 and 12, see rejection to claims 1 and 11 above which discusses ECG data being a predictive input as claimed.
Regarding claims 4 and 14:
Radzievsky in view Bhushan discloses the invention substantially as claimed including all the limitations of claims 1 and 11 as outlined above and a machine-learning model that includes a convolutional neural network as outlined in the rejections to claims 1 and 11 and a Bayesian classifier as one of the machine-learning models used.
However, Radzievsky in view Bhushan fails to disclose the convolutional neural network as comprising “a plurality of convolutional layers” as recited by claims 2 and 12.
It would have been obvious to one having ordinary skill in the art at the time the invention was filed to modify Radzievsky in view Bhushan’s convolutional neural network to include “a plurality of convolutional layers” because there are a limited number of possible choices of the number of convolutional layers in a convolutional neural network (i.e. one layer or a plurality of layers) and a plurality of convolutional layers is one those limited number of possible choices.
Regarding claims 8 and 18
Radzievsky in view of Bhushan discloses the invention substantially as claimed including all the limitations of claims 1 and 11 as outlined above and “receiving, by the system of one or more computers, ECG data that describes the at least
an ECG of the first subject over the period of time” as outlined above in rejection to claims 1 and 11. Also, Bhushan (which discloses the machine-learning model used by Radzuevsky in view of Bhushan and therefore is understood to be applied to Radzievsky in view of Bhushan as modified) also discloses the model as obtaining key ECG data from the PQRST complexes which is understood to recite “receiving a first ECG from a first cardiac cycle” [see para 107 of Bhushan…. “comprising of the ECG signal (132) and the SCG signal (133), which together denote several events of the cardiac cycle, including the P, Q, R, S and T complexes from the ECG”] and taking a mean (i.e. averaging) data including that of ECG data to generate averaged data which is understood to generate the predictive input as a function of the data [see para 51… “the Biostrip device records the ECG data at a frequency of anywhere between 125 Hz and 4 kHz, PPG data at a frequency of anywhere between 25 Hz and 2 kHz, Accelerometer data at a frequency of anywhere between 5 Hz and 2 kHz, and sends the data to the MCU, where the data is processed using mean/median/Bandpass filters, and automated peak detection algorithms annotate each signal, and calculate the timing of the electrical, mechanical and blood-flow related events in the cardiac cycle.”]
However, Radzievsky in view of Bhushan is silent as to the number of the ECG cardiac cycles used and therefore fails to fully disclose the limitations: “receiving a second ECG from a second cardiac cycle”, “processing, by the system, the ECG data to generate the predictive input comprises: averaging the first ECG and the second ECG to generate an averaged ECG and generating the predictive input as a function of the averaged ECG.” as claimed.
It would have been obvious to one having ordinary skill in the art at the time the invention was filed to use ECG data from the PQRST complexes of two or more cardiac cycle (i.e. thereby fully reciting claims 9 and 19) and then averaging the data (i.e. thereby reciting the missing limitations) because there are only a limited number of possible ways to obtain these complexes (i.e. from one singular cardiac cycle or from multiple cardiac cycles) and the use of multiple cardiac cycles (i.e. two or more) is one of those limited possible choices.
Regarding claims 9 and 19
Radzievsky in view of Bhushan discloses the invention substantially as claimed including all the limitations of claims 1 and 10 as outlined above. Bhushan (which discloses the machine-learning model used by Radzievsky in view of Bhushan) also discloses the model as obtaining key ECG data from the PQRST complexes (i.e. a subset of ECG data) cardiac cycle [see para 107 of Bhushan…. “comprising of the ECG signal (132) and the SCG signal (133), which together denote several events of the cardiac cycle, including the P, Q, R, S and T complexes from the ECG”].
However, Radzievsky in view of Bhushan fail to disclose if this subset comes from a single or multiple cardiac cycles. Therefore, Radzievsky in view of Bhushan fails to fully disclose the limitation:
“wherein processing by the system, the ECG data to generate the predictive input comprises selecting a subset of ECG data corresponding to a single cardiac cycle.”
It would have been obvious to one having ordinary skill in the art at the time the invention was filed to use ECG data from the PQRST complexes of a single cardiac cycle (i.e. thereby fully reciting claims 9 and 19) because there are only a limited number of possible ways to obtain these complexes (i.e. from one singular cardiac cycle or from multiple cardiac cycles) and one single cardiac cycle is one of those limited possible choices.
Regarding claims 10 and 20:
Radzievsky in view of Bhushan discloses the invention substantially as claimed including all the limitations of claim 1 and 11 as outlined above.
However, Radzievsky in view of Bhushan fails to disclose “pushing, by the system and a notification service, the subject structural heart disease prediction to a mobile computing device for display” as recited by claims 10 and 20.
Bhushan further discloses presenting an alert if a specific threshold is met to a smartphone and includes the alert being displayed (i.e. pushing by the system and a notification service) to user’s smartphone (i.e. mobile computing device for display) to warn a user [see para 79… “calculated to be above a certain threshold thresh>0, then an alert is sent to the User through the vibration motor, or the smartphone application. This gives an indication to the User to not exert themselves any further, as the capacity of the heart to increase contractility further is exhausted.” And para 90… “the system for cardiovascular health monitoring can send an alert through the gateway device and/or through the vibration motor and/or the LEDs and/or an electronic display on the Biostrip, when the ASR, as recorded by the procedure described herein crosses a certain pre-defined threshold.”].
It would have been obvious to one having ordinary skill in the art at the time the invention was filed to further modify Radzuevsky in view of Bhushan’s system so that when a heart disease prediction meets a threshold to push by the system and a notification service to a user’s smartphone to warn a user similarly to that disclosed by Bhushan (i.e. thereby reciting claims 10 and 20).
Claim(s) 3,5-6, 13 and 15-16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Radzievsky in view Bhushan as applied to claims 1-2 and 11-12 above, and further in view of Sinha et al (US 20170065230).
Regarding claims 3, 6, 13 and 16:
Radzievsky in view of Bhushan discloses the invention substantially as claimed including all the limitations of claims 1-2 and 11-12.
However, Radzievsky in view of Bhushan fails to disclose:
“wherein the training data is selected from a population of patients sharing the patient characteristic” as recited by claims 3 and 13 or “identifying a patient characteristic of the first subject, wherein selecting the machine-learning model from a plurality of machine-learning models is a function of the selected patient characteristic.” as recited by claims 6 and 16.
Sinha discloses in the analogous art of cardiovascular diagnostics [see abstract… “A method and system for acquiring data for assessment of cardiovascular disease, the method comprising one or more of: manipulating one or more hardware aspects of the photoplethysmography data acquisition system(s) implementing the method”] selecting and using data of a subpopulation can lead to specific biomarkers that can help with the diagnosis of people within the subpopulation [see Para 18… “additionally or alternatively include extracting a set of reference windows that are characteristic of different subpopulations of individuals, upon processing reference windows of time series image data from a population of individuals in association with a set of characterizations of the population of individuals S165, which can function to generate “biomarkers” that can be used to diagnose, characterize, or facilitate data processing for different populations or/subpopulations of individuals, as described in more detail below.”]
It would have been obvious to one having ordinary skill in the art at the time the invention was filed to modify Radziveksy in view of Bhushan’s machine learning to be trained on data related to a subpopulation (i.e. thereby reciting wherein the training data is selected from a population of patients sharing the patient characteristic and identifying a patient characteristic of the first subject, wherein selecting the machine-learning model from a plurality of machine-learning and models is a function of the selected patient characteristic selected from a population of patients sharing the patient characteristic) because as taught by Sinha identifying and using data related to a subpopulation of individuals can allow for the use of specific biomarkers unique to individuals within the subpopulation which can further aid in the diagnosis of said shared subpopulation leading to the expectation of a high accuracy in the diagnosis.
Regarding claims 5 and 15
Radzievsky in view of Bhushan discloses the invention substantially as claimed including all the limitations of claims 1-2 and 11-12.
However, Radzievsky in view of Bhushan fails to disclose: “wherein the machine-learning model further comprises one or more layers of perceptrons comprising associated weights for activation functions associated with each perceptron” as recited by claims 5 and 15
Sinha discloses in the analogous art of cardiovascular diagnostics [see abstract… “A method and system for acquiring data for assessment of cardiovascular disease, the method comprising one or more of: manipulating one or more hardware aspects of the photoplethysmography data acquisition system(s) implementing the method”] that an Artificial neural network that uses perceptron method (i.e. understood to recite one or more layers of perceptrons with associated weights as claimed) is a known type of neural network used in processing and analysis of cardiovascular data [see para 65… “Additionally or alternatively, Block S160 can implement a machine learning algorithm that is trained with a training dataset (e.g., training data acquired from another measurement device). In variations, the machine learning algorithm can be characterized by a learning style including any one or more of:…an artificial neural network model (e.g., a Perceptron method, a back-propagation method”]
It would have been obvious to one having ordinary skill in the art at the time the invention was filed to modify Radzievsky in view of Bhushan to include the selection of an Artificial neural network that uses a perceptron method similarly to that disclosed by Sinha because this is a known machine-learning algorithm in cardiovascular diagnostics and will lead to greater range in analyzing cardiovascular data.
Claim(s) 7 and 17 is/are rejected under 35 U.S.C. 103 as being unpatentable over Radzievsky in view Bhushan as applied to claims 1 and 11 above, and further in view of Simopoulos et al (US 20080009722) hereafter known as Simopoulos.
Radzievsky in view Bhushan discloses the invention substantially as claimed including all the limitations of claims 1 and 11 as outline above. Furthermore, Radzievsky in view Bhushan discloses using Bayesian classifiers as one of the choices of machine-learning model [see rejection to claim 1 above and para 44 of Bhushan… “In various embodiments, the data stored on the web for multiple Users, is used in Machine learning algorithms such as a convolutional neural networks and/or Bayesian Classifiers and/or support vector machines, to distinguish between healthy and pathological conditions of the User in question, by using the stored and annotated data as a training set, and applying the classification algorithms on the User's data.”].
However, Radzievsky in view Bhushan is silent as to all the details of the Bayesian classifiers used. Therefore, Radzievsky in view Bhushan fails to disclose “wherein the machine-learning model comprises a binary-classification model configured to classify the predictive input into one of two categories” as recited by claims 7 and 17
Simopoulos discloses in the analogous art of cardiovascular diagnostics binary Bayesian classifiers are a known type of Bayesian classifier used to analyze the heart [see para 30… “Any classifier may be applied, such as a model based classifier or a learned classifier or classifier based on machine learning. For learned classifiers, binary or multi-class classifiers may be used, such as Bayesian or neural network classifiers. In one embodiment, a multi-class boosting classifier with a tree and cascade structure is used. The classifier is instructions, a matrix, a learned code, or other software and/or hardware for distinguishing between information in a medical image. Learned feature vectors are used to classify the anatomy. For example, the classifier identifies a canonical view, tissue structure, flow pattern, or combinations thereof from ultrasound data. In cardiac imaging, the classifier may identify cardiac structure associated with a particular view of a heart. The view is a common or standard view (e.g., apical four chamber, apical two chamber, left parasternal, or sub-coastal), but other views may be recognized. The cardiac structure is the heart walls or other structure defining the view or a structure associated with the view. For example, a valve associated with an apical four chamber view is identified.”]
Since Radzievsky in view Bhushan discloses using Bayeisan classifiers but is silent as to all the details of the Bayesian classifiers used and Simopoulos discloses that binary-classification models are a known type of Bayesian classifier used in cardiovascular diagnostics, it would have been obvious to one having ordinary skill in the art at the time the invention was filed to modify Radzievsky in view Bhushan to specifically use a binary-classification Bayesian classifier similarly to that described by Simopoulos (i.e. thereby reciting claims 7 and 17) because this is a known type of machine-learning models used in cardiovascular diagnostics.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SEBASTIAN X LUKJAN whose telephone number is (571)270-7305. The examiner can normally be reached Monday - Friday 9:30AM-6PM.
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, NIKETA PATEL can be reached at 571-272-4156. 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.
SEBASTIAN X LUKJAN
/SXL/Examiner, Art Unit 3792
/NIKETA PATEL/Supervisory Patent Examiner, Art Unit 3792
Prosecution Insights