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 .
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.
1. Claims 10-29 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. The independent claims 10 and 26 recite a computer-implemented method/system for facilitating an LVSD diagnosis of a subject “based on signal processing analysis of morphological changes in electrocardiogram signal data the method comprising: accessing, by a computer system, electrocardiogram (ECG) signal data obtained from a subject; inputting, by the computer system, the ECG signal data into a pre-trained neural network model, the pre-trained neural network model trained based at least in part on correlations between morphological changes in ECG signal data and occurrence of cardiac dysfunction obtained from a plurality of other subjects, the morphological changes in ECG signal data determined computationally, wherein the morphological changes in the ECG signal data comprises visibly observable and non-visibly observable changes in one or more of shape, size, or duration of a P wave, QRS wave, or T wave; and generating, by the computer system, a likelihood of presence or occurrence of cardiac dysfunction for the subject based on an output of the pre- trained neural network model, wherein the generated likelihood of presence or occurrence of cardiac dysfunction is configured to be used to diagnose the subject”. The limitation, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components. For example, someone could look at ECG data and then make determinations on if the subject is experiencing LVSD by looking at the ECG waveforms. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. This judicial exception is not integrated into a practical application.
The components are recited at a high-level of generality such that it amounts no more than any structure that can look at data and male predictions. Further, the use of processors and storage means in the dependent claims, are merely insignificant extra-solution activity of data gathering. Accordingly, these additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claim is directed to an abstract idea.
The additional elements, such as the processor and storage means, while being mere structures for data analysis/storing are also well-understood, routine, conventional activity that is widely prevalent or common use in the relevant industry. The use of processors and storage means to analyze and store patient information are well known in the art as disclosed by the following references: US 20190090774 A1 and US 20200205745 A1. Well-understood, routine and conventional activity cannot be significantly more than the abstract idea itself. The claims are not patent eligible.
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.
2. Claim(s) 10-17 and 21-29 is/are rejected under 35 U.S.C. 103 as being unpatentable over Yang (US 20190090774 A1) in view of Khosousi (US 20200205745 A1).
In regards to claims 10 and 26, Yang discloses a computer-implemented method of facilitating diagnosis of a subject based on signal processing analysis of morphological changes in electrocardiogram signal data (Abstract teaches a computer system to diagnosing cardiac abnormalities from ECG data), the method comprising:
accessing, by a computer system, electrocardiogram (ECG) signal data obtained from a subject (Par. 0029 teaches gathering data from a 12 lead ECG);
inputting, by the computer system, the ECG signal data into a pre-trained neural network model, the pre-trained neural network model trained based at least in part on correlations between morphological changes in ECG signal data and occurrence of cardiac dysfunction obtained from a plurality of other subjects, the morphological changes in ECG signal data determined computationally, wherein the morphological changes in the ECG signal data comprises visibly observable and non-visibly observable changes in one or more of shape, size, or duration of a P wave, QRS wave, or T wave (Par. 0029 teaches inputting the ECG data into a neural network to determine cardiac dysfunction. Par. 0039 teaches that the neural network is trained with training samples from ECG lead data. Par. 0007 and 0030 teaches looking at the changes in QRS waveform data) and
generating, by the computer system, a likelihood of presence or occurrence of cardiac dysfunction for the subject based on an output of the pre- trained neural network model, wherein the generated likelihood of presence or occurrence of cardiac dysfunction is configured to be used to diagnose the subject (Par. 0041-0043 teach that the system uses the neural network to determine the probability that a cardiac abnormality is occurring and where it is occurring),
wherein the computer system comprises a computer processor and an electronic storage medium (Par. 0062 discloses the device having processors and a storage means).
While Yang teaches using neural networks and ECG data to determine the possibility of cardiac abnormalities, they do not explicitly teach diagnosing left ventricular systolic dysfunction (Yang does teach monitoring the left ventricle, just not making any diagnosis of the left ventricle specifically). However, in the same field of endeavor, Khosousi discloses a method for using neural networks and ECG data (Abstract and Par. 0004) to determine if a user is experiencing LVSD (Par. 0013) in order to identify and prevent heart disease before it can cause harmful effects (Par. 0015).
Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to have taken the teachings of Yang and modified them by having the system monitor for LVSD, as taught and suggested by Khosousi, in order to identify and prevent heart disease before it can cause harmful effects (Par. 0015 of Khosousi).
In regards to claim 11 and 27, the combined teachings of Yang and Khosousi disclose the computer-implemented method of Claim 10/26, further comprising preprocessing, by the computer system, the accessed ECG signal data prior to inputting the ECG signal data into the pre-trained neural network model, the preprocessing comprising down-sampling and augmenting the ECG signal data by applying noise (Par. 0037 of Yang teaches down-sampling the ECG data).
In regards to claims 12-13 and 28-29, the combined teachings of Yang and Khosousi disclose the computer-implemented method of Claim 10/26, wherein the pre- trained neural network model comprises a plurality of sub-neural network models, each of the plurality of sub-neural network models configured to receive ECG signal data from one or more ECG leads as input, wherein the pre- trained neural network model is configured to selectively use one or more of the sub-neural network models (Par. 0037 of Yang teaches the neural network using/implementing CNNs, i.e. sub-neural network models).
In regards to claim 14, the combined teachings of Yang and Khosousi disclose the computer-implemented method of Claim 12, wherein the pre- trained neural network model is configured to combine outputs of a plurality of the sub-neural network models in generating the likelihood of presence or occurrence of left ventricular systolic dysfunction for the subject (Par. 0041-0043 of Yang teach that the system uses the neural networks/CNNs to determine the probability that a cardiac abnormality is occurring and where it is occurring. Par. 0013 and 0159 of Khosousi also teaches using CNNs and determining if LSVD is occurring).
In regards to claim 15, the combined teachings of Yang and Khosousi disclose the computer-implemented method of Claim 12, wherein the plurality of sub-neural network models comprises a first sub-neural network model configured to receive ECG signal data from 12 ECG leads as input, a second sub-neural network model configured to receive ECG signal data from at least 6 limb leads or 6 precordial leads, and a third sub-neural network model configured to receive ECG signal data from one or more single leads (Par. 0039-0041 of Yang teaches using all 12 leads within the CNN blocks and also just using the half of the 12 leads, i.e. 6 leads. Par. 0060 also teaches using single lead pacing).
In regards to claim 16, the combined teachings of Yang and Khosousi disclose the computer-implemented method of Claim 10, wherein the accessed ECG signal data comprises ECG signal data acquired from 12 ECG leads (Par. 0004 of Yang teaches using a 12 lead ECG).
In regards to claim 17, the combined teachings of Yang and Khosousi disclose the computer-implemented method of Claim 10, wherein the accessed ECG signal data comprises ECG signal data acquired from fewer than 12 ECG leads (Par. 0039 of Yang teaches using 6 leads from the ECG).
In regards to claim 21, the combined teachings of Yang and Khosousi disclose the computer-implemented method of Claim 10, wherein the pre- trained neural network model comprises a plurality of residual blocks, wherein each of the plurality of residual blocks comprises a plurality of sub-modules (Par. 0022-0024 of Yang teaches using blocks)
In regards to claim 22, the combined teachings of Yang and Khosousi disclose the computer-implemented method of Claim 21, wherein the sub- modules comprise one or more of a convolutional neural network (CNN), batch normalization, ReLU activation function layer, or a dropout layer (Par. 0022 of Yang teaches using CNNs)
In regards to claim 23, the combined teachings of Yang and Khosousi disclose the computer-implemented method of Claim 21, wherein a sub-module comprises a max pooling layer configured to perform input to a ReLU activation function layer (Par. 0037 and 0039 of Yang teaches using pooling layers).
In regards to claim 24, the combined teachings of Yang and Khosousi disclose the computer-implemented method of Claim 10, wherein the morphological changes in the ECG signal data comprises a change in one or more of PR segments, QRS segments, pathological Q waves, poor R progression, ST depression, T wave inversion, atrial premature beats, or ventricular premature beats (Par. 0007 and 0030 teaches looking at the changes in QRS waveform data)
In regards to claim 25, the combined teachings of Yang and Khosousi disclose the computer-implemented method of Claim 10, except for wherein the generated likelihood of presence or occurrence of left ventricular systolic dysfunction is configured to be used to diagnose peripartum cardiomyopathy, wherein pre-trained neural network model is trained based on correlations between morphological changes in ECG signal data obtained from a plurality of other subjects during a week prior to delivery and occurrence of left ventricular systolic dysfunction.
While the teachings of Yang and Khosousi as applied to claim 10 do not teach this limitation, Khosousi does go on to teach using the LVSD to monitor for cardiomyopathy (Par. 0013) in order to monitor for heart disease before harmful effects can take place. Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to have the system use the LVSD to monitor for cardiomyopathy, as further taught by Khosousi, in order to monitor for heart disease before harmful effects can take place (Par. 0013 of Khosousi).
3. Claim(s) 18-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Yang and Khosousi, and in further view of Li (US 20190167143 A1).
In regards to claim 18, the combined teachings of Yang and Khosousi disclose the computer-implemented method of Claim 10, except for wherein the pre- trained neural network model is further configured to receive biological data of the subject as input, the biological data comprising one or more of gender, age, weight, or height of the subject (While Khosousi teaches using biological data sets in their analysis, they do not explicitly teach that data being gender, age, weight, or height of the subject).
However, in the same field of endeavor, Li teaches a system for analyzing ECGs for abnormalities in the left ventricular region using neural networks (Abstract and Par. 0078) wherein the neural networks can also gather information about the patients age (Par. 0075) in order to make patient specific estimations (Par. 0075).
Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to have taken the teachings of Yang and modified them by having the system take in age information about the patient, as taught and suggested by Li, in order to make patient specific estimations (Par. 0075 of Li).
In regards to claim 19, the combined teachings of Yang, Khosousi, and Li disclose the computer-implemented method of Claim 18, further comprising standardizing, by the computer system, one or more of the ECG signal data or the biological data prior to inputting into the pre-trained neural network model (Par. 0035 of Yang teaches using the standardized segmentation).
In regards to claim 20, the combined teachings of Yang, Khosousi, and Li as applied to claim 18 disclose the computer-implemented method of Claim 18, except for wherein the pre-trained neural network model comprises a fully connected layer configured to receive the biological data.
While the teachings of Yang, Khosousi, and Li as applied to claim 18 do not teach this limitation, Khosousi does go on to teach using fully connected layers (Par. 0086) in order to define a family of functions that are parameterized by the weights of the network elements (Par. 0076 of Khosousi). Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to have the system using fully connected layers, as further taught and suggested by Khosousi, in order to define a family of functions that are parameterized by the weights of the network elements (Par. 0076 of Khosousi).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SKYLAR LINDSEY CHRISTIANSON whose telephone number is (571)272-0533. The examiner can normally be reached Monday-Friday, 7:30-5:30 EST.
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.
/S.L.C./Examiner, Art Unit 3792
/NIKETA PATEL/Supervisory Patent Examiner, Art Unit 3792