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 .
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.
Drawings
The drawings are objected to under 37 CFR 1.83(a). The drawings must show every feature of the invention specified in the claims. Therefore, the generation of class activation data and associated limitations of new claims 21-24 must be shown or the feature(s) canceled from the claim(s). No new matter should be entered.
Corrected drawing sheets in compliance with 37 CFR 1.121(d) are required in reply to the Office action to avoid abandonment of the application. Any amended replacement drawing sheet should include all of the figures appearing on the immediate prior version of the sheet, even if only one figure is being amended. The figure or figure number of an amended drawing should not be labeled as “amended.” If a drawing figure is to be canceled, the appropriate figure must be removed from the replacement sheet, and where necessary, the remaining figures must be renumbered and appropriate changes made to the brief description of the several views of the drawings for consistency. Additional replacement sheets may be necessary to show the renumbering of the remaining figures. Each drawing sheet submitted after the filing date of an application must be labeled in the top margin as either “Replacement Sheet” or “New Sheet” pursuant to 37 CFR 1.121(d). If the changes are not accepted by the examiner, the applicant will be notified and informed of any required corrective action in the next Office action. The objection to the drawings will not be held in abeyance.
Claim Rejections - 35 USC § 112
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claims 5 and 15 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention.
The examiner cannot find in the original disclosure where it is disclosed that an indication of the level of confidence that the second episode of arrhythmia has occurred in the patient corresponds to the first arrhythmia type. Note also the comments below in the rejection of said claims under §112(b).
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 5 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 5 is confusing. Claim 1 states that the second episode of arrhythmia corresponds to a second arrhythmia type, while claim 5 indicates that the device is configured to update one or more of the indications that the second episode of arrhythmia has occurred in the patient, the at least a portion of the cardiac electrogram data, or the indication of the level of confidence that the second episode of arrhythmia has occurred in the patient to correspond to the first arrhythmia type. If the second episode of arrhythmia corresponds to the second arrhythmia type (claim 1), then it is unclear how it simultaneously corresponds to the first arrhythmia type (claim 5). Related comments apply to similarly worded claim 15.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-3, 5, 7-13, 15 and 17-24 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
The claim(s) recite(s) the mentally performable process of applying a machine learning model to the received cardiac electrogram data for each type of a plurality of arrhythmia types, wherein the machine learning model comprises a neural network-based machine learning model trained using cardiac electrogram data for a plurality of patients, determining, based on the applying of the machine learning model to the received cardiac electrogram data, that a first episode of arrhythmia has occurred in the patient, wherein the first episode of arrhythmia corresponds to a first arrhythmia type of the plurality of arrhythmia types; determining a level of confidence in the determination that the episode of arrhythmia has occurred in the patient; determine, based on the applying of the machine learning model to the received cardiac electrogram data, that second episode of arrhythmia has occurred in the patient, wherein the second episode of arrhythmia corresponds to a second arrhythmia type of the plurality of arrhythmia types; determining a level of confidence in the determination that the second episode of arrhythmia has occurred in the patient; and determining that the level of confidence in the determination that the second episode of arrhythmia has occurred in the patient is greater than a predetermined first threshold and less than a second threshold, wherein the level of confidence in the determination that the first episode of arrhythmia has occurred in the patient is greater than the first threshold and greater than the second threshold.
The inclusion of a machine learning model and a neural network fails to restrict the invention to a non-mentally performable task. There are no limitations as to the complexity or type of machine learning/neural network-based model; no limitations as to the amount of cardiac data received and processed; and no limitations as to the accuracy of arrhythmia detection. The applicant discloses in par. 0070 that machine learning may apply mathematical operations, such as linear algebraic, nonlinear, or alternative computation operations. Such computation operations are considered reasonably mentally performable (or with pen and paper).
This judicial exception is not integrated into a practical application because there are no improvements to the functioning of a computer, or to any other technology or technical field (the storage medium, processing circuitry and display operate in their usual capacity, alone and in combination), as discussed in MPEP 2106.05(a); there is no application or use of a judicial exception to effect a particular treatment or prophylaxis for disease or medical condition – see Vanda Memo; there is no application of the judicial exception with, or by use of, a particular machine, as discussed in MPEP 2106.05(b), but only generic components in generic arrangements; there is no transformation or reduction of a particular article to a different state or thing, as discussed in MPEP 2106.05(c), but only data manipulation; and there is no application or use of the judicial exception in some other meaningful way beyond generally linking the use of the judicial exception to the particular technological environment of cardiac signal processing, such that the claim as a whole is more than a drafting effort designed to monopolize the exception, as discussed in MPEP 2106.05(e) and the Vanda Memo issued in June 2018.
The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the storage medium, the processing circuitry configured to receive cardiac electrogram data and display device are generic in form and function in their usual capacity –whether individually or in combination. The storage medium represents insignificant extra-solution activity that would be required in any and every implementation of the invention to store data and programming information. The processing circuitry functions in its usual capacity of receiving and processing data and merely acts as the tool upon which the abstract idea is performed. The receipt of cardiac electrogram data by the processor (it is noted that the medical device for sensing alluded to in claim 1 is not positively recited) and the generic display are considered insignificant extra-solution activity that would be required in any implementation of the abstract idea in order to provide necessary data gathering and tailoring a human perceptible output of the processing results in accordance with a user’s request. A change in the content of information presented to a user does not represent an improvement in the technology itself, as the content presented merely reflects the user’s preferences.
The storage medium, the processing circuitry and display device, individually and in combination, are WURC in the art as every computing device requires such elements. The applicant states that the storage medium may consist of volatile or non-volatile memory such as conventional RAM, DRAM, SRAM or hard discs, floppy discs, flash memories, EPROM or EEPROM, or any other digital media (par. 0045). The processing circuitry is disclosed to be any one or more of a conventional microprocessor, controller, DSP, ASIC, FPGA or equivalent discrete or analog logic circuitry (par. 0046). The display may comprise any number of conventional devices, including CRT monitors, LCDs or any other type of display device for converting a signal into an appropriate form understandable to humans or machines (par. 0066).
Regarding the limitation pertaining to not outputting for display an indication that the first episode of arrhythmia has occurred in the patient, as stated in MPEP 2106.05(a):
If it is asserted that the invention improves upon conventional functioning of a computer, or upon conventional technology or technological processes, a technical explanation as to how to implement the invention should be present in the specification. That is, the disclosure must provide sufficient details such that one of ordinary skill in the art would recognize the claimed invention as providing an improvement. The specification need not explicitly set forth the improvement, but it must describe the invention such that the improvement would be apparent to one of ordinary skill in the art. Conversely, if the specification explicitly sets forth an improvement but in a conclusory manner (i.e., a bare assertion of an improvement without the detail necessary to be apparent to a person of ordinary skill in the art), the examiner should not determine the claim improves technology. An indication that the claimed invention provides an improvement can include a discussion in the specification that identifies a technical problem and explains the details of an unconventional technical solution expressed in the claim, or identifies technical improvements realized by the claim over the prior art.
In the instant case, there is no improvement upon the conventional functioning of a computer, or upon conventional technology or technological processes because the additional elements (i.e., the storage medium, processing circuitry and display device) function in their usual capacity, alone and in combination. The applicant asserts that there may be an improvement of increased accuracy in diagnosis, but it appears that the display is merely presenting the information requested of it by the user. Such a request has no effect on the functioning of the computer itself or to the functioning of any other technological system.
Furthermore, even if one were to concede that an improvement in technology exists and would be recognizable to one of ordinary skill, as stated in MPEP 2106.05(a):
After the examiner has consulted the specification and determined that the disclosed invention improves technology, the claim must be evaluated to ensure the claim itself reflects the disclosed improvement in technology. Intellectual Ventures I LLC v. Symantec Corp., 838 F.3d 1307, 1316, 120 USPQ2d 1353, 1359 (Fed. Cir. 2016) (patent owner argued that the claimed email filtering system improved technology by shrinking the protection gap and mooting the volume problem, but the court disagreed because the claims themselves did not have any limitations that addressed these issues). That is, the claim must include the components or steps of the invention that provide the improvement described in the specification.
The current disclosure states that by allowing a user to select a specific arrhythmia of interest, the computing system may filter the output to depict the presence of only the selected type(s) of arrhythmia on a location within the cardiac electrogram data, as well as a corresponding confidence level in the detection, thus presumably prominently allowing the display of arrhythmias of interest that have been detected with a low confidence level. Claims 1 and 11, however, do not include any limitations regarding user selection of a specific arrhythmia of interest, and thus fail to reflect the alleged improvement. Further, while claims 5 and 15 reference receiving a user input via a user input device, the user input and display operate in their usual capacity of receiving information and displaying requested information to the user. Also note the comments above regarding the rejection of claims 5 and 15 under §112(b).
Regarding claims 2 and 3, the limitations recited therein represent insignificant data outputting that would be required in most any system attempting to process cardiac electrogram data and indicate the results of said processing including the indication of detected arrhythmias and an indication of the determined confidence level. The applicant states in par. 0084 that the computing system may use a wide variety of different visualization techniques to convey information to the user.
Regarding claim 5, note the comments above pertaining to the outputting of information for display and the comments under §112 above. As stated, the user input device functions in its usual capacity of collecting user preference information and such devices are WURC in cardiac diagnostic computing devices. A variety of conventional user input devices are listed in par. 0065.
Claims 7-10, 21 and 23 do not contain any additional elements and can be performed within the mind or with pen and paper.
The analysis of patentably indistinct method claims 11-13, 15 and 17-20 parallel the analysis already given above for claims 1-3, 5 and 7-10.
Regarding new claims 22 and 24, the outputting of egm data on a display, where the information presented represents that portion of the egm that exhibits the arrhythmia and that caused the neural network to assign the arrhythmia type, relates to insignificant data outputting recited with a high level of generality that is WURC in any neural network (e.g., Class Activation Mapping (CAM), heatmaps, etc., which are specific mechanisms known to be useful in conveying information as to how the network made its determinations, thus improving model transparency, interpretability and trustworthiness). Such a display allows only the relevant portions of data that are of most interest to the user to be presented, thus simplifying the display and analysis.
Claim Rejections - 35 USC § 103
The text of those sections of Title 35, U.S. Code not included in this action can be found in a prior Office action.
Claim(s) 1-3, 5, 7-9, 11-13, 15 and 17-19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Zhang et al. (Pub. No. 2010/0312130) in view of Perschbacher et al. (Pub. No. 2017/0290550) and Gunderson et al. (Pat. No. 8,744,560).
Regarding claim 1, Zhang discloses a computing device comprising: a storage medium 208; and processing circuitry 206 operably coupled to the storage medium (Fig. 2) and configured to: receive cardiac electrogram data sensed by a medical device (Fig. 2); determine that an episode of ischemia has occurred in the patient (par. 0009); determine a level of confidence in the determination that the episode of ischemia has occurred in the patient (par. 0003); determine that the level of confidence in the determination that the episode of ischemia has occurred in the patient is greater than a predetermined threshold (e.g., greater than a moderate or low confidence level); and in response to determining that the level of confidence is greater than the predetermined threshold (e.g., when a high confidence level is determined), output for display to a user an indication that the episode of ischemia has occurred in the patient (e.g., when a high confidence level is determined, a response can be initiated to a physician indicating the high confidence level of an ischemic event; pars. 0066-0069).
While Zhang determines a confidence level associated with an ischemic event, there is no explicit discussion of determining a confidence level associated with an arrhythmia. Perschbacher, however, discloses a related computing device that determines confidence levels associated with arrhythmias (see title, abstract). Perschbacher further teaches that the invention is not limited to arrhythmias, but may be configured to process events other than cardiac arrhythmias including ischemic cardiomyopathy and other suitably equivalent conditions (par. 0072). Gunderson as well teaches that confidence levels for the various arrhythmia detections may be established (col. 6, lines 22-39). Clearly those of ordinary skill in the art given Perschbacher’s and Gunderson’s teachings that one is not limited to determining the confidence level of any one detected disease or cardiac condition, would have considered it an obvious matter of design to determine the confidence level associated with an arrhythmia determination in the system of Zhang.
Regarding the limitation concerning receiving cardiac electrogram data for each type of a plurality of arrhythmia types, an electrogram is considered to contain data for any of a variety of cardiac arrhythmia types (e.g., information about tachycardia, fibrillation, flutter, etc., is all inherently contained within an electrogram). It is also noted that Perschbacher discloses that the arrhythmia detector may detect a variety of different arrhythmias (pars. 0010, 0057) as well as Gunderson (col. 2, lines 20-39). The exact diseases or maladies detected clearly depends on physician preference and the medical condition of the patient. Clearly if the patient is subject to a number of different arrhythmias, then it would behoove one to receive data for each type of arrhythmia in order to adequately diagnose and treat the totality of potential patient conditions.
Once it has been established that it is beneficial to detect a plurality of arrhythmia types, expanding the confidence determination to each of the plurality of arrhythmia types would have been blatantly obvious to those of ordinary skill in the art. Clearly if it is desirable to establish the confidence level for at least one arrhythmia determination as suggested by Zhang in view of Perschbacher, then it would be obvious to duplicate the same process for establishing confidence levels for at least a second arrhythmia episode of a plurality of arrhythmia types. Gunderson additionally states that episodes of various arrhythmias may include classification confidence analysis (col. 6, lines 22-39; col. 13, lines 33-61, etc.).
Regarding the use of a first and second threshold, Zhang discloses that a variety of responses may be issued dependent upon the confidence level, where for example, a medium confidence may initiate a moderately aggressive response, while a high confidence level may initiate an aggressive response (pars. 0067-0074). The medium confidence level is considered to represent a level greater than a first threshold (i.e., the level considered to delineate the low confidence level from the medium confidence level) and lower than a second threshold (i.e., the level considered to delineate the medium confidence level from the high confidence level). A high confidence level is axiomatically greater than a medium confidence level, and thus considered to represent a level greater than both the first threshold (low) and the second threshold (medium). Zhang thus allows for the determination of a level of confidence that a second episode of arrhythmia that has occurred in a patient is greater than a first threshold and less than a second threshold, as well as a level of confidence that a first episode of arrhythmia that has occurred in the patient is greater than the first threshold and greater than the second threshold.
As discussed in the aforementioned paragraphs and shown in the corresponding tables, a moderately aggressive response (i.e., as initiated by a medium confidence level) can include outputting data for display in human-readable form and include data related to sensed or measured ischemic or arrhythmia episodes (par. 0033). Those of ordinary skill in the art would have readily recognized such events to include at least a portion of the cardiac electrogram (egm) corresponding to the episode of the arrhythmia, because a review of the egm data associated with the arrhythmia would be of great concern to any cardiologist desiring to confirm diagnosis and/or better understand the patient’s condition. Gunderson, for example, teaches that EGM data may be included in the information transmitted to an external device for display (col. 4, lines 23-30, col. 8, lines 50-62, col. 17, lines 4-20, etc.).
Regarding the application of a machine learning model to the received ECG data, wherein the model comprises a neural network-based machine learning model and determining an episode of arrhythmia based on the machine learning model trained using ECG data for a plurality of patients, while Zhang discloses using a machine learning model comprising a neural network-based machine learning model to determine the confidence level that an ischemic event has been detected (par. 0058), Zhang does not discuss using a machine model to determine an episode of arrhythmia (see pars. 0031-0033 where Zhang discloses that arrhythmias may also be detected). The determination of an arrhythmia using machine learning is, however, old and well known in the art as discussed by Perschbacher (pars. 0065 and 0094). It is taught that machine learning provides more computational power and thus may have higher sensitivity or specificity and can process large amounts of data (par. 0065). To employ the recited machine learning model to the received ECG data in order to improve arrhythmia detection would have therefore been considered obvious in the art. It is also noted that training the model using ECG data for a plurality of patients would have necessarily been required in any system attempting to learn how to detect arrhythmias from ECG data.
Regarding the limitation involving not displaying an indication that a first episode of arrhythmia has occurred in a patient, Gunderson, in a related device and method, teaches that a customizable subset of information may be presented to a user based on user input in order to limit the amount of information presented to the user (col. 4, lines 11-22). It is further taught that episodes selected for inclusion in the report may be prioritized by the physician or other user (e.g., by selecting the episodes that are most likely to be of interest to the physician/user), along with confidence level classification (col. 6, lines 8-40; col. 21, line 48- col. 22, line 18). Clearly if a user were concerned with only a particular type of arrhythmia, those of ordinary skill in the art would have considered it obvious to allow the user the ability to restrict the information presented to only the particular arrhythmia episode of interest, excluding other episodes that might overwhelm a user by presenting unnecessary and/or undesired information (i.e., the user may input their own priority rules as taught by Gunderson). If for example, a user was interested in seeing indications of atrial fibrillation (AF) episodes, but not necessarily indications of bradycardia episodes, it would have been obvious to those of ordinary skill in the art in view of Gunderson, to allow a user to be presented with only the episodes of interest (i.e., the AF episodes), even if the episode(s) of interest had a lower confidence level than that of other detected episodes, in order to satisfy the user’s preferences.
Regarding claim 2, see pars. 0021, 0022, 0063 and 0070 of Perschbacher which teaches to output at least a portion of the prioritized two or more detected arrhythmic events. Such events include portions of waveforms of the signal/cardiac cycle and include characteristic points. Those of ordinary skill in the art would have recognized that annotations of ECG waveforms are standard in the art and used to provide a human perceivable indication of characteristic points of interest in the cardiac cycle. Gunderson, for example, teaches that annotations may be included in a related system and method (col. 6, lines 40-61).
Regarding claim 3, see par. 0065 which discloses outputting an indication of the level of confidence via graphical or textual notification.
Regarding claim 5, in response to determining that the level of confidence is greater than a predetermined threshold (e.g., greater than either the low or moderate confidence levels), an indication of the level of confidence is output to the user (pars. 0068 and 0069). Also, as argued above in the rejection of claim 2, at least a portion of the ECG data would have been obvious to send so as to inform the nurse or physician as to the condition of the patient. As disclosed by Perschbacher, user input may be received via a user input device 251 allowing a user to program the parameters used for sensing the physiological signals and detecting the arrhythmias (par. 0070; see also comments above with respect to the application of Gunderson). As disclosed in par. 0057, a variety of cardiac arrhythmias may be included in the analysis. To allow the user to program the type of arrhythmia to be sensed and detected from the variety of arrhythmias that the device may detect would have been considered blatantly obvious to those of ordinary skill in the art because such a feature enhances the device’s capabilities and allows the user to tailor the detection to suit the needs of the patient.
Regarding claim 7, see par. 0031 and 0033 of Zhang (tachyarrhythmia), as well as par. 0080 of Perschbacher (or, for example, col. 6, lines 22-39, etc. of Gunderson) and the motivation to determine confidence levels for detected arrhythmias as discussed above.
Regarding claim 8, note the comments above concerning the obviousness of using machine learning models to process the data. Labeling of training data to indicate the presence of arrhythmia episodes would be required in any machine learning model attempting to detect arrhythmias and would certainly have been considered an obvious expediency to provide the machine with valid examples of arrhythmias by anyone of ordinary skill in the art.
Regarding claim 9, applying a machine learning model to at least ECG data would have been obvious as discussed above in the rejection of claim 1 to allow for the processing of large amounts of data.
The rejection of claims 11-13, 15 and 17-19 parallel the rejection of claims 1-3, 5 and 7-9 above.
Claim(s) 10 and 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Zhang et al. (Pub. No. 2010/0312130) in view of Perschbacher et al. (Pub. No. 2017/0290550) and Gunderson et al. (Pat. No. 8,744,560) as applied to claims 1-3, 5, 7-9, 11-13, 15 and 17-19 above, and further in view of Bardy et al. (Pub. No. 2016/0192853).
Zhang and Perschbacher do not disclose the limitations of claim 10. Bardy, however, discloses as is old and well-known in the art, that by outputting subsections of the ECG comprising periods prior to, during, and after clinically meaningful episodes of arrhythmia (i.e., a “snapshot” of shorter duration than the collected ECG; see par. 0042), the physiological context of the arrhythmia may be captured, resulting in enhanced specificity and diagnostic abilities (par. 0042). Artisans of ordinary skill in the art would have therefore considered it obvious to include such beneficial features in the device and method of Zhang as modified by Perschbacher and Gunderson.
Claim(s) 21-24 is/are rejected under 35 U.S.C. 103 as being unpatentable over Zhang et al. (Pub. No. 2010/0312130) in view of Perschbacher et al. (Pub. No. 2017/0290550) and Gunderson et al. (Pat. No. 8,744,560) as applied to claims 1-3, 5, 7-9, 11-13, 15 and 17-19 above, and further in view of Goodfellow et al. (article entitled: ECG Classification Using Convolutional Neural Networks and Attention Mappings”).
Regarding claims 21 and 23, while Zhang, Perschbacher and Gunderson disclose the generation of data indicating the likelihoods of a second (or first) arrhythmia type over time as the electrogram is processed, they do not disclose the identification limitation of claims 21 and 23. Goodfellow, however, in a related ECG diagnostic system, discloses the generation of class activation data over time for ECG arrhythmia classification in neural networks, where one or more regions of the received ECG that caused the neural network learning model to assign the arrhythmia type using class activation data is identified (see for example Fig. 8, CAM, and associated text). Goodfellow teaches that such maps provide an improved understanding of the inner workings of a CNN ECG rhythm classifier (page 3, par. 2), which helps to allow some level of interpretability by clinicians, which is likely important for the adoption of these techniques to augment diagnosis (abstract). Artisans of ordinary skill in the art looking to provide users with a better insight into the workings of the CNN rhythm classifier, thus aiding in the interpretability of such rhythms, would have considered it obvious to include such a feature into the neural network-based learning model defined by Zhang and Perschbacher.
Regarding claims 22 and 24, as discussed above, Zhang, Perschbacher and specifically Gunderson, teach to output for display at least a portion of the cardiac electrogram data corresponding to the second episode of arrhythmia. Goodfellow, as discussed above, teaches to identify one or more regions of the received ECG data that caused the neural network-based learning model to assign a particular rhythm classification using class activation data. Those of ordinary skill in the art looking to provide the clinician with a better level of interpretability of the results, would have therefore considered a feature known to enhance a user’s understanding of the diagnostic results, thus augmenting diagnosis, to be obvious.
Response to Arguments
Applicant's arguments filed April 14, 2026 have been fully considered but they are not persuasive.
Regarding the rejection of newly amended claims 5 and 15 under §112, note the discussion in the rejection above.
Regarding the rejection under §101, the applicant argues that the current claim set is analogous to Example 39 detailed in the July 2019 Subject Matter Eligibility guidelines, in that amended claim 1 recites a neural network-based machine learning model trained using cardiac electrogram data for a plurality of patients, which allegedly cannot be practically performed in the human mind, and thus does not recite any judicial exception. It is further argued that like Example 39, the present claims are directed to a computing device and a method of operating a computing device for performing cardiac diagnostics by applying a machine learning model to cardiac electrogram data.
The mere fact that the claims utilize neural network-based machine learning is insufficient to establish eligibility. Examples 47-49 of the July 2024 Subject Matter Eligibility Examples, for instance, also list claims which recite the use of neural network-based machine learning, and yet each example includes claims considered ineligible. Clearly the recitation of a computer or, in this case, neural network-based machine learning is alone insufficient. In the case of Example 39, the claim did not contain any feature that could be reasonably performed within the mind, as the mind is not reasonably capable of transforming digital images including applying mirroring, rotating, smoothing or contrast reduction to create a modified set of digital facial images, and then using these images to create a training set for training a neural network. In contrast, the present invention includes actions that can be performed within the human mind (e.g., determining that episodes of arrhythmia have occurred, determining a level of confidence in the determinations, comparing confidence levels to threshold values). Like the presence of a conventional computer, the presence of a conventional neural network to apply the judicial exception does not qualify as a particular machine. It functions merely as a tool upon which the judicial exception is executed.
Regarding the rejection of claims under §103 as it relates to the newly amended claims, please note the comments made in the rejection above and the application of Gunderson to account for the limitation pertaining to filtering display information such that an indication that the first episode of arrhythmia has occurred in the patient is not displayed.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to KENNEDY SCHAETZLE whose telephone number is (571)272-4954. The examiner can normally be reached on the 2nd Monday of the biweek and W-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, David E. Hamaoui can be reached on 571 270 5625. 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.
/KENNEDY SCHAETZLE/Primary Examiner, Art Unit 3796
KJS
July 6, 2026
Prosecution Insights