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 § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claim 7 and 15 are 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.
Claim 7 recites the limitation "the previously generated atrial fibrillation model" in line 11. There is insufficient antecedent basis for this limitation in the claim. Precedent is not set forth for generating an atrial fibrillation model, and therefore, it is unclear what is considered the previously generated atrial fibrillation model. Further, it is unclear if this is the same model from line 1 of claim 7 (the pretrained model), or if the previously generated atrial defibrillation model is distinct from the pretrained atrial defibrillation model of claim 1 (line 8). For examination purposes, the previously generated model and the pretrained model will be considered as the same model.
Claim 15 is rejected for the same issue.
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.
Claim 1-16 rejected under 35 U.S.C. 101 because the claimed subject matter is directed towards an abstract idea without significantly more than an abstract idea.
Step 1- Is the claim to a statutory category of invention?
Claims 1-8 recite a method. Claim 9-16 recite a machine (i.e., a device).
Step 2A, prong 1- Does the claim recite a judicial exception?
Regarding claim 1, the claim recites “determining a patient’s risk of developing atrial fibrillation using the preprocessed electrocardiogram data and a pretrained atrial fibrillation determination model.” This is both a mental process and mathematical concept abstract idea. “Using the preprocessed electrocardiogram data and pretrained atrial fibrillation determination model” is a mathematical concept in that the model inputs the data into algorithms to make calculations. Further, determining a risk of developing atrial fibrillation is a mental process in that one of ordinary skill in the art, such as a physician, could observe ECG data to determine a patient’s risk of developing atrial fibrillation. Further, this determination could be made in the physician’s head.
Regarding claim 9, the claim recites similar mental process and mathematical concept abstract ideas as detailed in claim 1. The only difference between the claimed invention is the implementation of the abstract ideas into a determination unit. The same explanation outlining the judicial exception for claim 1 applies to claim 9.
Step 2A, prong 2- Does the claim recite additional elements that integrate the judicial exception into a practical application?
Regarding claim 1, the claim recites “a method for detecting signs of atrial fibrillation in normal sinus rhythm, the method comprising: acquiring electrocardiogram data of a patient; generating preprocessed electrocardiogram data based on at least some specific regions from the electrocardiogram data.” The claimed subject matter does not integrate the abstract idea into a practical application. Acquiring ECG data and generating preprocessed data from an ECG amounts to insignificant, pre-solution activity data gathering, and does not implement the abstract idea into a practical application.
Regarding claim 9, the claim recites “ an electrocardiogram data processing unit configured to acquire electrocardiogram data of a patient and generate preprocessed electrocardiogram data based on at least some specific regions from the electrocardiogram data; and an atrial fibrillation determination unit.” As outlined in claim 1, the claimed subject matter does integrate the abstract idea into a practical application, and is merely insignificant pre-solution activity data gathering. Further, the claim implements the abstract idea into generic computer structures defined by the methods of performing abstract ideas. Doing so does not amount to integration of an abstract idea into a practical application.
Step 2B- Do the additional elements add significantly more to the judicial exception?
Regarding claim 1, the claim recites “a method for detecting signs of atrial fibrillation in normal sinus rhythm, the method comprising: acquiring electrocardiogram data of a patient; generating preprocessed electrocardiogram data based on at least some specific regions from the electrocardiogram data.” The claimed subject matter does not amount to significantly more than the judicial exception. The claimed subject matter is recited with a high level of generality. Acquiring ECG data and generating preprocessed data from an ECG amounts to insignificant, pre-solution activity data gathering.
Regarding claim 9, the claim recites “ an electrocardiogram data processing unit configured to acquire electrocardiogram data of a patient and generate preprocessed electrocardiogram data based on at least some specific regions from the electrocardiogram data; and an atrial fibrillation determination unit.” As outlined in claim 1, the claimed subject matter does not amount to significantly more than an abstract idea, and is merely insignificant pre-solution activity data gathering. Further, the claim implements the abstract idea into generic computer structures defined by the methods of performing abstract ideas. Doing so does not amount to significantly more than an abstract idea.
Dependent claims
Claim 2, 3, 5, 10, 11, and 13 further limit extra-solution data gathering.
Claim 4 and 12 further limit a mathematical concept.
Claims 6 and 14 further limits data gathering and introduces an abstract idea mental process (comparing data to a threshold value). The claims also recite a generic computer function (transmitting).
Claims 7 and 15 further limit data gathering and further defines a mathematical concept abstract idea (performing training of the determination model).
Claim 8 and 16 further limit a mental process abstract idea and mental concept abstract idea.
Claims 10-16 recite the same abstract ideas of 1-8, the difference being that they are implemented using generic computer structures (processing unit and training unit).
In summary, claims 1-16 are directed to a judicial exception without significantly more.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claim(s) 1, 3, 4, 5, 6, 9, 11, 12, and 13 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Li et al. (US 20230352180 A1, “Li”).
Regarding claim 1, Li teaches a method for detecting signs of atrial fibrillation in normal sinus rhythm (abstract; "The invention provides an atrial fibrillation risk prediction system based on heartbeat rhythm signals"), the method comprising: acquiring electrocardiogram data of a patient (para. [0035]; "The RR interval samples extracted from the heartbeat signals of different patients."; para. [0031]; "Take ECG signal as an example, detect the R wave peak of the collected ECG signal.”); generating preprocessed electrocardiogram data based on at least some specific regions from the electrocardiogram data (para. [0039]; "The heartbeat signals of a patient is preprocessed to obtain a series of RR interval sample.”); and determining a patient’s risk of developing atrial fibrillation using the preprocessed electrocardiogram data and a pretrained atrial fibrillation determination model (para. [0039]; " The heartbeat signals of a patient is preprocessed to obtain a series of RR interval samples, the obtained RR interval samples are input into the trained AF risk prediction model to obtain the output probability of each sample, and different output probability thresholds are set. Therefore, An AF risk curve between the proportion of positive samples and the probability thresholds is obtained.").
Regarding claim 3, Li teaches the method according to claim 1 (see above), wherein the generating of the preprocessed electrocardiogram data (para. [0039]; "The heartbeat signals of a patient is preprocessed to obtain a series of RR interval sample.”) comprises dividing the preprocessed electrocardiogram data into input data of a first preset time (para. [0012]; "Furthermore, the steps to divide RR interval sequence are as follows: based on a non-overlapping sliding window, the RR interval sequence is divided from its initial position to obtain the RR interval samples, and after each division, the sliding window is moved forward by one window for a next division"; the sliding window represents a time.”) to generate an input data set (para. [0038]; "The AF risk prediction model is configured to input heartbeat rhythm signals into the heartbeat rhythm signal preprocessing module to obtain multiple RR interval samples and input the multiple RR interval samples into the AF risk prediction model to obtain the output probability corresponding to each RR interval sample.")
Regarding claim 4, Li teaches the method according to claim 3 (see above), wherein the pretrained atrial fibrillation determination model is configured to output a probability of the patient’s risk of developing atrial fibrillation corresponding to the input of the input data set. (para. [0038]; "The AF risk prediction model is configured to input heartbeat rhythm signals into the heartbeat rhythm signal preprocessing module to obtain multiple RR interval samples and input the multiple RR interval samples into the AF risk prediction model to obtain the output probability corresponding to each RR interval sample.").
Regarding claim 5, Li teaches the method according to claim 1 (see above), further comprising generating an analysis report on the risk of developing atrial fibrillation (Fig. 3; Atrial fibrillation risk curve).
Regarding claim 6, Li teaches the method of claim 5 (see above). Li is silent to the condition of if a patient’s risk of developing atrial fibrillation exceeds a preset value. Therefore, the limitation of transmitting the analysis report to a preset device of a medical institution is not required by the claim. The Li meets the limitations of claim 6 since the limitations of claim 5 are taught by Li.
Regarding claim 9, Li teaches a device for detecting signs of atrial fibrillation in normal sinus rhythm (abstract; "The invention provides an atrial fibrillation risk prediction system based on heartbeat rhythm signals"), the device comprising: an electrocardiogram data processing unit (para. [0030]; “A heartbeat rhythm signal preprocessing module.”) configured to acquire electrocardiogram data of a patient and generate preprocessed electrocardiogram data based on at least some specific regions from the electrocardiogram data (para. [0030]; A heartbeat rhythm signal preprocessing module is configured to extract the RR interval value between two consecutive heartbeats in the heartbeat rhythm signals and obtain the RR interval sequence.”); and an atrial fibrillation determination unit (para. [0039]; “the trained AF risk prediction model.”) configured to determine a patient’s risk of developing atrial fibrillation using the preprocessed electrocardiogram data and a pretrained atrial fibrillation determination model (para. [0039]; " The heartbeat signals of a patient is preprocessed to obtain a series of RR interval samples, the obtained RR interval samples are input into the trained AF risk prediction model to obtain the output probability of each sample, and different output probability thresholds are set. Therefore, An AF risk curve between the proportion of positive samples and the probability thresholds is obtained.").
Regarding claim 11, Li teaches the device according to claim 9 (see above), wherein the electrocardiogram data processing unit (para. [0008];” a heartbeat rhythm signal preprocessing module. This module was used to extract the RR interval value between two consecutive heartbeats in the heartbeat rhythm signals to obtain the RR interval sequence. Then, the RR interval sequence was divided at equal intervals to obtain multiple RR interval samples.”) divides the preprocessed electrocardiogram data into input data of a first preset time (para. [0012]; "Furthermore, the steps to divide RR interval sequence are as follows: based on a non-overlapping sliding window, the RR interval sequence is divided from its initial position to obtain the RR interval samples, and after each division, the sliding window is moved forward by one window for a next division"; the sliding window represents a time.) to generate an input data set (para. [0038]; "The AF risk prediction model is configured to input heartbeat rhythm signals into the heartbeat rhythm signal preprocessing module to obtain multiple RR interval samples and input the multiple RR interval samples into the AF risk prediction model to obtain the output probability corresponding to each RR interval sample.").
Regarding claim 12, Li teaches the device according to claim 11 (see above), wherein the pretrained atrial fibrillation determination model is configured to output a probability of the patient’s risk of developing atrial fibrillation corresponding to the input of the input data set. (para. [0038]; "The AF risk prediction model is configured to input heartbeat rhythm signals into the heartbeat rhythm signal preprocessing module to obtain multiple RR interval samples and input the multiple RR interval samples into the AF risk prediction model to obtain the output probability corresponding to each RR interval sample.")
Regarding claim 13, Li teaches the device according to claim 9 (see above), further comprising a determination result processor (processing unit) (para. [0017]; “The invention further provides an AF risk prediction device including a processor and a machine-readable storage medium. The machine-readable storage medium stores machine-executable instructions executed by the processor. The processor executes the machine-executable instructions to implement specific functions of the AF risk prediction system based on heartbeat rhythm signals according to the foregoing description.”). Li is silent to the condition where if the patient’s risk of developing atrial fibrillation exceeds a preset reference value, the processing unit generates an analysis report on the risk of developing atrial fibrillation. Therefore, it is not required that the device needs to meet the condition, or that it must generate an analysis report. Li’s device meets the limitations of claim 13.
Claim(s) 1, 7, 9, and 15 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Umemoto et al. (US 20230049898 A1, “Umemoto”).
Regarding claim 1, Umemoto discloses a method for detecting signs of atrial fibrillation in normal sinus rhythm (para. [0049]; “FIG. 1 illustrates a configuration of a prediction device 10 according to an embodiment. The prediction device 10 is configured to predict a risk of atrial fibrillation occurring in a subject 30 based on an electrocardiogram waveform obtained from the subject 30 through an electrocardiograph 20.”), the method comprising: acquiring electrocardiogram data of a patient (para. [0049;” The prediction device 10 is configured to predict a risk of atrial fibrillation occurring in a subject 30 based on an electrocardiogram waveform obtained from the subject 30 through an electrocardiograph 20.”) generating preprocessed electrocardiogram data based on at least some specific regions from the electrocardiogram data (para. [0083]; “As illustrated in FIG. 3, the reception unit 61 of the training data generation device 60 may be configured as an interface through which third data D3 can be obtained. The third data D3 is generated based on an electrocardiogram waveform obtained from a subject 32 by the electrocardiograph 21.”); and determining a patient’s risk of developing atrial fibrillation using the preprocessed electrocardiogram data and a pretrained atrial fibrillation determination model (para. [0081]; “Therefore, a learned model generated through machine learning using such training data can output a prediction result that there is a risk of occurrence of atrial fibrillation, with respect to an input of an electrocardiogram waveform in which sinus rhythm is determined.”).
Regarding claim 7, Umemoto discloses the method according to claim 1 (above), wherein the pretrained atrial fibrillation determination model is trained through a process comprising: acquiring training electrocardiogram data including first normal sinus rhythm data of patients with a history that atrial fibrillation is developed and second normal sinus rhythm data of patients without the history that atrial fibrillation is developed (para. [0083]; “As illustrated in FIG. 3, the reception unit 61 of the training data generation device 60 may be configured as an interface through which third data D3 can be obtained. The third data D3 is generated based on an electrocardiogram waveform obtained from a subject 32 by the electrocardiograph 21. The subject 32 is different from the subject 31. For example, the subject 31 may be a patient having a medical history of atrial fibrillation, whereas the subject 32 may be a patient not having a medical history of atrial fibrillation.”); labeling (para. [0082]; “In addition, the first training label indicating that atrial fibrillation has occurred is assigned a weighting index that can take a plurality of values according to the time interval.”; Umemoto discloses here that he also uses labeling) the first normal sinus rhythm data and the second normal sinus rhythm data with distinguished marks (para. [0083]; The subject 32 is different from the subject 31. For example, the subject 31 may be a patient having a medical history of atrial fibrillation, whereas the subject 32 may be a patient not having a medical history of atrial fibrillation.”; The patients are different and distinguished as having a history and not having a history); and causing the previously generated atrial fibrillation determination model to perform training using the training electrocardiogram data (para. [0081]; “Therefore, a learned model generated through machine learning using such training data can output a prediction result that there is a risk of occurrence of atrial fibrillation, with respect to an input of an electrocardiogram waveform in which sinus rhythm is determined. Accordingly, it is possible to predict a risk of occurrence of atrial fibrillation potentially possessed by a subject.”).
Regarding claim 9, Umemoto discloses a device for detecting signs of atrial fibrillation in normal sinus rhythm (prediction device 60; Fig. 3), the device comprising: an electrocardiogram data processing unit (Fig. 3; reception unit 61) configured to acquire electrocardiogram data of a patient and generate preprocessed electrocardiogram data based on at least some specific regions from the electrocardiogram data (Para. [0066]; “Subsequently, the processing unit 62 obtains the second data D2 through the reception unit 61 (STEP 13 in FIG. 5). That is, the processing unit 62 obtains data including an electrocardiogram waveform in which it is determined that atrial fibrillation has not occurred.”); and an atrial fibrillation determination unit (Fig. 3; output unit 63) configured to determine a patient’s risk of developing atrial fibrillation using the preprocessed electrocardiogram data and a pretrained atrial fibrillation determination model (para. [0145]; “Therefore, a learned model, which is generated through machine learning using such training data, can output a prediction result that there is a risk of disease development, with respect to an input of physiological information based on which it can be determined that a disease is not developing. Accordingly, a disease development risk potentially possessed by a subject can be predicted.”).
Regarding claim 15, Umemoto discloses the device according to claim 9 (see above), further comprising an atrial fibrillation determination model training unit (Fig. 3; training data generation device 60) configured to cause the atrial fibrillation determination model to perform training, wherein the atrial fibrillation determination model training unit performs training (para. [0138]; “A second aspect of the presently disclosed subject matter relates to A training data generation device that generates training data to be used in generating a learned model for predicting a disease development risk of a subject based on physiological information obtained from the subject.”) of the pretrained atrial fibrillation determination model by acquiring training electrocardiogram data including first normal sinus rhythm data of patients with a history that atrial fibrillation is developed and second normal sinus rhythm data of patients without the history that atrial fibrillation is developed (para. [0083]; “As illustrated in FIG. 3, the reception unit 61 of the training data generation device 60 may be configured as an interface through which third data D3 can be obtained. The third data D3 is generated based on an electrocardiogram waveform obtained from a subject 32 by the electrocardiograph 21. The subject 32 is different from the subject 31. For example, the subject 31 may be a patient having a medical history of atrial fibrillation, whereas the subject 32 may be a patient not having a medical history of atrial fibrillation.”); labeling (para. [0082]; “In addition, the first training label indicating that atrial fibrillation has occurred is assigned a weighting index that can take a plurality of values according to the time interval.”; Umemoto discloses here that he also uses labeling) the first normal sinus rhythm data and the second normal sinus rhythm data with distinguished marks (para. [0083]; The subject 32 is different from the subject 31. For example, the subject 31 may be a patient having a medical history of atrial fibrillation, whereas the subject 32 may be a patient not having a medical history of atrial fibrillation.”; The patients are different and distinguished as having a history and not having a history); and causing the previously generated atrial fibrillation determination model to perform training using the training electrocardiogram data (para. [0081]; “Therefore, a learned model generated through machine learning using such training data can output a prediction result that there is a risk of occurrence of atrial fibrillation, with respect to an input of an electrocardiogram waveform in which sinus rhythm is determined. Accordingly, it is possible to predict a risk of occurrence of atrial fibrillation potentially possessed by a subject.”).
Claims 1 and 8 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Choi et al. (“Diagnosis of atrial fibrillation based on AI-detected anomalies of ECG segments.”; Pub. Date: December 12, 2023, “Choi”).
Regarding claim 1, Choi teaches a method for detecting signs of atrial fibrillation in normal sinus rhythm (abstract; “a novel AF diagnosis system.”), the method comprising: acquiring electrocardiogram data of a patient (Materials and methods, 2.1; “Our study utilized two public datasets, the PTB-XL dataset and the China dataset provided by PhysioNet. The PTB-XL dataset was recorded from 1989 to 1996 in Germany, and it comprises 21,837 clinical 12-lead ECG records from 18,885 patients”); generating preprocessed electrocardiogram data based on at least some specific regions from the electrocardiogram data (Materials and methods, 2; “shows an overview of the overall study, which comprises preprocessing, training dataset for the model, DL model, and anomaly detection.”); and determining a patient’s risk of developing atrial fibrillation using the preprocessed electrocardiogram data and a pretrained atrial fibrillation determination model (abstract; “To address these limitations, in this study, we proposed a novel AF diagnosis system using unsupervised learning for anomaly detection with three segments, PreQ, QRS, and PostS, based on the normal ECG”).
Regarding claim 8, Choi teaches the method according to claim 1 (see above), wherein the pretrained atrial fibrillation determination model (abstract; “AF diagnosis system”; “deep learning”) is configured to determine the patient’s risk of developing atrial fibrillation based on at least some of ST segments and QRS complexes of the preprocessed electrocardiogram data (abstract; “To address these limitations, in this study, we proposed a novel AF diagnosis system using unsupervised learning for anomaly detection with three segments, PreQ, QRS, and PostS, based on the normal ECG.”; PostS is considered as an ST segment.)
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.
Claim(s) 2 and 10 are rejected under 35 U.S.C. 103 as being unpatentable over Li et al. (US 20230352180 A1, “Li”) in view of Lee et el. (WO 2020141807 A2, “Lee”).
Regarding claim 2, Li discloses the method according to claim 1. However, Li does not disclose wherein the generating of the preprocessed electrocardiogram data comprises removing at least a portion of a first region preset before a specific P-peak and a second region preset after a specific T-peak from the electrocardiogram data.
Lee, in the same field of endeavor of methods for predicting atrial fibrillation using machine learning, discloses a method for processing and inputting data into a deep learning model. Lee discloses wherein the generating of the preprocessed electrocardiogram data comprises removing at least a portion of a first region preset before a specific P-peak and a second region preset after a specific T-peak from the electrocardiogram data. (para. [0044]; The pre-processing unit 110 may cut an electrical biosignal from which baseline drift has been removed based on the extracted R-peak index to an R-R interval and remove outliers according to the RRI length.” Although not explicitly disclosed removing a region before the P-peak and after the T-peak (the TR intetrval), Lee discloses removing outliers (signal noise). This can include the baseline TR interval that occurs between T and P peaks).
It would have been obvious to one of ordinary skill in the art before the effective filing date to include the method of removing portions of the ECG signal to reduce signal noise with the methods of claim 1, as disclosed by Li. The process of removing segments of the ECG in preprocessing is a known technique that yields predictable results. It would have been obvious to remove regions to that are not relevant to the data input into the prediction model since this would reduce signal noise. Further, It would have been obvious to try this removal process with the segment of the signal before the P-peak and after the T-wave. The ECG has a finite number of components (P, Q, R, S, and T) and intervals between them. It would have been obvious to one of ordinary skill in the art to try removing different segments to reduce signal noise and find which result yields the most accurate prediction.
Regarding claim 10, Li discloses the device according to claim 9 (see 102 rejection above). However, Li does not disclose wherein the electrocardiogram data processing unit removes at least a portion of a first region preset before a specific P-peak and a second region preset after a specific T-peak from the electrocardiogram data.
Lee discloses wherein the electrocardiogram data (para. [0044]; “The pre-processing unit 110”) processing unit removes at least a portion of a first region preset before a specific P-peak and a second region preset after a specific T-peak from the electrocardiogram data. (para. [0044]; The pre-processing unit 110 may cut an electrical biosignal from which baseline drift has been removed based on the extracted R-peak index to an R-R interval and remove outliers according to the RRI length.” Although not explicitly disclosed removing a region before the P-peak and after the T-peak (the TR intetrval), Lee discloses removing outliers (signal noise). This can include the baseline TR interval that occurs between T and P peaks).
It would have been obvious to one of ordinary skill in the art before the effective filing date to include an electrocardiogram processing unit configured to perform method of removing portions of the ECG signal to reduce signal noise with the device of claim 9, as disclosed by Li. The process of removing segments of the ECG in preprocessing is a known technique that yields predictable results. It would have been obvious to include a processor to remove regions to that are not relevant to the data input into the prediction model since this would reduce signal noise. Further, It would have been obvious to try including a processor for this removal process with the segment of the signal before the P-peak and after the T-wave. The ECG has a finite number of components (P, Q, R, S, and T) and intervals between them. It would have been obvious to one of ordinary skill in the art to try removing different segments to reduce signal noise and find which result yields the most accurate prediction.
Claim(s) 6, 13 and 14 are rejected under 35 U.S.C. 103 as being unpatentable over Li et al. (US 20230352180 A1, “Li”) in view of de Saint Victor et al. (US 20220095982 A1, “de Saint Victor”).
Regarding claim 6, Li discloses the method according to claim 5. However, Li is silent to the condition where if a patient’s risk exceeds a preset reference value, transmitting the analysis report to a preset device of a medical institution.
De Saint Victor discloses a method comprising if the patient’s risk of developing atrial fibrillation exceeds a preset reference value (para. [0027]; “It is further understood that the second plurality of instructions may, when executed, analyze the ECG data of the patient using at least one algorithm that applies the ECG data to a second neural network for classification. Specifically, the second plurality of instructions may quantify a likelihood of a presence of the one or more abnormalities, conditions, or descriptors, and may apply a threshold to at least one value in the output of the second neural network and assign at least one label corresponding to the one or more abnormalities, conditions, or descriptors if the value exceeds a threshold.”), transmitting the analysis report to a preset device of a medical institution (para. [0028]; “The system may further include a fourth and/or fifth plurality of instructions. The fourth plurality of instructions may, when executed, cause the at least one server to generate a report including at least the transmitted information corresponding to the presence of the one or more abnormalities, conditions, or descriptors.”).
It would have been obvious for one of ordinary skill in the art before the effective filing date to include the method of exceeding a threshold and alerting medical staff with the methods of claim 1, as disclosed by Li. Alerting the medical staff after the risk score exceeds a threshold is an obvious improvement to the technique of predicting atrial fibrillation since the purpose of the Li’s device is to predict atrial fibrillation. Severe rhythm abnormalities are known to require immediate medical attention, and therefore, it would have been obvious to report these abnormalities.
Regarding claim 13, Li discloses the device according to claim 9 (see 102 rejection above), further including a processor (processing unit) (para [0017]; “The invention further provides an AF risk prediction device including a processor and a machine-readable storage medium. The machine-readable storage medium stores machine-executable instructions executed by the processor. The processor executes the machine-executable instructions to implement specific functions of the AF risk prediction system based on heartbeat rhythm signals according to the foregoing description.”). However, Li does not disclose where the processing unit is configured to, if the patient’s risk of developing atrial fibrillation exceeds a preset reference value, generate an analysis report to on the risk of developing atrial fibrillation.
De Saint Victor discloses where the device is configured to, if the patient’s risk of developing atrial fibrillation exceeds a preset reference value (para. [0027]; “It is further understood that the second plurality of instructions may, when executed, analyze the ECG data of the patient using at least one algorithm that applies the ECG data to a second neural network for classification. Specifically, the second plurality of instructions may quantify a likelihood of a presence of the one or more abnormalities, conditions, or descriptors, and may apply a threshold to at least one value in the output of the second neural network and assign at least one label corresponding to the one or more abnormalities, conditions, or descriptors if the value exceeds a threshold.”), generate an analysis report to on the risk of developing atrial fibrillation. (para. [0028]; “The system may further include a fourth and/or fifth plurality of instructions. The fourth plurality of instructions may, when executed, cause the at least one server to generate a report including at least the transmitted information corresponding to the presence of the one or more abnormalities, conditions, or descriptors.”).
It would have been obvious for one of ordinary skill in the art before the effective filing date to include the configuration for exceeding a threshold and alerting medical staff with the atrial fibrillation processor and device of claim 9. Alerting the medical staff after the risk score exceeds a threshold is an obvious improvement to the technique of predicting atrial fibrillation since the purpose of the Li’s device is to predict atrial fibrillation. Severe rhythm abnormalities are known to require immediate medical attention, and therefore, it would have been obvious to report these abnormalities. Further, it would have been obvious to include this function in a processor since a processor is well known computer structure capable of executing instructions for predictive models.
Regarding claim 14, Li, in combination with De Saint Victor, discloses the device according to claim 13 (see above). De Saint Victor further discloses wherein the determination result processing unit transmits the analysis report to a preset device of a medical institution (para. [0028]; “The system may further include a fourth and/or fifth plurality of instructions. The fourth plurality of instructions may, when executed, cause the at least one server to generate a report including at least the transmitted information corresponding to the presence of the one or more abnormalities, conditions, or descriptors.”).
It would have been obvious to one of ordinary skill in the art before the effective filing date to include the processing unit, as disclosed by Li, with the instructions for transmitting the report. Improving the processor to configure it to transmit a report is an obvious improvement to a device that is predicting the risk of atrial fibrillation. Improving the device to report the analysis to a medical institution would have been obvious since the medical staff would be able to address cardiac abnormalities from the transmitted report.
Claim 16 is rejected under 35 U.S.C. 103 as being unpatentable over Li et al. (US 20230352180 A1, “Li”) in view of Choi et al. (“Diagnosis of atrial fibrillation based on AI-detected anomalies of ECG segments.”; Pub. Date: December 12, 2023, “Choi”).
Regarding claim 16, Li discloses the device according to claim 9 (see 102 rejection above). However, Li does not disclose wherein the pretrained atrial fibrillation determination model is configured to determine the patient’s risk of developing atrial fibrillation based on at least some of ST segments and QRS complexes of the preprocessed electrocardiogram data.
Choi discloses wherein the pretrained atrial fibrillation determination model (abstract; “AF diagnosis system”; “deep learning”) is configured to determine the patient’s risk of developing atrial fibrillation based on at least some of ST segments and QRS complexes of the preprocessed electrocardiogram data (abstract; “To address these limitations, in this study, we proposed a novel AF diagnosis system using unsupervised learning for anomaly detection with three segments, PreQ, QRS, and PostS, based on the normal ECG.”; PostS is considered to be a part of an ST segment.).
It would have been obvious to one of ordinary skill in the art before the effective filing date to include the device of claim 9, as disclosed by Li, with the configuration to perform the function of detecting atrial fibrillation using the ST segments and QRS complex, as disclosed by Choi. It would have been obvious to try using the QRS and ST segments since Choi discloses using these segments in a predictive model for atrial fibrillation. It would have been obvious to select those segments as and use them in a predictive model as Choi does. Further, it would have been obvious to combine this with the device of claim 9 since Li is also attempting to predict the occurrence of atrial fibrillation.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to OWEN LEWIS MARSH whose telephone number is (571)272-8584. The examiner can normally be reached 7:30am -5pm (M-Th) and 8am – noon (F).
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, Jennifer McDonald can be reached at (571) 270-3061. 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.
/OWEN LEWIS MARSH/Examiner, Art Unit 3796
/Jennifer Pitrak McDonald/Supervisory Patent Examiner, Art Unit 3796