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 Interpretation
For the purpose of examination, the first claim 39 will be labeled as claim 39(i) and the second claim 39 will be labeled as claim 39(ii).
Status of Claims
Claims 1-3, 5-7, 26-31, 33-34, 36-37, 39(i), 39(ii), and 40 are rejected. Claims 4, 8-25, 32, 35, and 38 are canceled.
Response to Arguments
Claim Objections
The previous claim objection of claim 37 has been withdrawn in view of the amendment.
Rejection under 35 U.S.C. § 112
Some of the previous 112(a) rejections have been withdrawn in view of the amendment.
Regarding claim 1, Applicant asserts the language has been moved to dependent claims 39 and 40. Applicant cites to ¶106 and ¶116-118 for support. However, a recommendation for adjustment is not the same as performing an adjustment as claimed. See the rejection below for further details.
Regarding claim 4 that is now amended into claim 1, Applicant asserts that ¶86 teaches unduly noisy and ¶15, ¶66, ¶87, and ¶100 teach the use of threshold. However, the original claims, specification, or drawings do not discuss unduly noisy detection together with a threshold. Therefore, the specification does not reasonably convey to the person of ordinary skill the claim element at issue.
Regarding claim 5, Applicant asserts that the specification reasonably conveys to the person of ordinary skill the claim element at issue. However, the original claims, specification, and drawings do not state “sensing parameter” as claimed.
Regarding claim 6, Applicant asserts the amendments clarify that the external device represents a local external device. However, the original claims, specification, and drawings do not state the external device represents a local external device as claimed.
Regarding claim 36, Applicant asserts that ¶58, ¶67, and ¶117 teach claim 36. However, the original claims, specification, or drawings do not discuss the IMD memory storing the adjustment to reprogram the sensing parameter. Therefore, the specification does not reasonably convey to the person of ordinary skill the claim element at issue.
Rejection under 35 U.S.C. §§ 102 and 103
Applicant's arguments filed 3/19/26 have been fully considered but they are not persuasive.
Applicant asserts that Perschbacher does not make up for the deficiency of Dani. Applicant specifically states that there is no suggestion in Dani or Perschbacher that a machine learning model need provide a confidence indicator. However, the Examiner disagrees. Dani was relied upon for the teaching of the machine learning algorithm (¶37-a machine learning model). Perschbacher was relied upon solely to teach i) a confidence indicator indicative of a degree of confidence that the corresponding DCA data set (¶8-a confidence indicator indicating a confidence level of the detection of the arrhythmic event) represents a true positive or false positive designation of an arrhythmia of interest (¶32-confidence-based arrhythmia detection, false positive, false determinations). Both references relate to arrhythmia detection. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Dani to include i) a confidence indicator indicative of a degree of confidence that the corresponding DCA data set represents a true positive or false positive designation of an arrhythmia of interest of Persch in order for detecting and managing cardiac arrhythmias (Persch, ¶2).
Applicant asserts that the combination does not teach the amended limitation of “utilized in connection with identifying at least one of P waves, R waves and T waves in the DCA data sets” in claims 28-29. However, the Examiner disagrees. An teaches identifying a Q wave and if a measured increase in the Q-S1 time duration may indicate an increased risk of the subject experiencing a WHF event (¶185). An additionally teaches prediction by the WHF detection algorithm is adjusted according to the determined HF risk score. For example, detection thresholds may be adjusted to be more easily satisfied in order to increase the sensitivity of HF detection (¶175).
Regarding claim 30, Applicant asserts that Sirendi does not teach or suggest artificially generated or computer-generated CA signals, where the CA signals and DD markers are based on actual DCA data sets collected from a patient. However, the Examiner disagrees. Claim 30 does not recite artificially generated or computer-generated CA signals. Instead, Sirendi teaches wherein the ML model represents a model that is trained utilizing an augmented collection of DCA data sets, wherein the augmented collection of the DCA data sets includes reference DCA data sets from patients (¶205-threshold values are determined based upon past data from multiple sources, for example a database containing physiological data for patients alongside occurrences of cardiac events may be used for training a classifier) and synthetic DCA data sets that are generated based on the reference DCA data sets (¶39; ¶42-Gaussian process, improved classifier; ¶139).
Claim Objections
Claims 39 are objected to because of the following informalities: There are 2 claims numbered 39. For the purpose of examination, the first claim 39 will be labeled as claim 39(i) and the second claim 39 will be labeled as claim 39(ii). Applicant is encouraged to correct claim 39(ii) to claim 40 and claim 40 to claim 41. Appropriate correction is required.
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 1-3, 5-7, 26-31, 33-34, 36-37, 39(i), 39(ii), and 40 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.
Claim 1 recites “wherein an unduly noisy DCA data set is determined using a threshold.” While ¶10 of the specification discloses:
the ML model outputs, in connection with each DCA data set, may include: i) a confidence indicator indicative of a degree of confidence that the corresponding DCA data set represents a true positive or false positive designation of an arrhythmia of interest; ii) a confidence indicator indicative of an accuracy of R-wave sensing implemented by the IMD; iii) a recommendation indicative of a sensitivity level to be utilized by the IMD to identify R waves in the CA signals; or iv) an output indicating that a particular DCA data set is unduly noisy and should not be characterized as a normal sinus rhythm, nor an arrhythmia.
this is not the same as the limitation as claimed. The specification does not disclose the unduly noise DCA data set being determined using a threshold. This limitation is neither recited in the originally filed claims, shown in the originally filed drawings, or disclosed in the originally filed specification. Therefore, it is new matter and fails to comply with the written description requirement.
Claim 5 recites “analyze the CA signals, utilizing the sensing parameter.” While ¶11 of the specification discloses:
The IMD may include a combination of subcutaneous electrodes configured to collect the CA signals. The IMD memory may be configured to store program instructions. One or more IMD processors may be configured to execute the program instructions to: analyze the CA signals and based on the analysis declare candidate arrhythmias episodes, generate the DCA data sets including the corresponding CA signals and the corresponding DD markers and a transceiver configured to wirelessly transmit the DCA data sets to an external device.
this is not the same as the limitation as claimed. The specification does not disclose analyzing the CA signals utilizing the sensing parameter. These limitations are neither recited in the originally filed claims, shown in the originally filed drawings, or disclosed in the originally filed specification. Therefore, it is new matter and fails to comply with the written description requirement.
Claim 6 recites “wherein the external device represents a local external device.” While ¶12 of the specification discloses:
an external device that includes the memory and the one or more processors and a transceiver. The transceiver may be configured to wirelessly receive the DCA data sets from the IMD.
this is not the same as the limitation as claimed. The specification does not disclose the local external device being the external device. This limitation is neither recited in the originally filed claims, shown in the originally filed drawings, or disclosed in the originally filed specification. Therefore, it is new matter and fails to comply with the written description requirement.
Claim 36 recites “wherein the IMD comprises IMD memory configured to store the adjustments to reprogram the sensing parameter to reduce the number of false positive candidate arrhythmias episodes declared by the IMD.” While ¶106 of the specification discloses:
the ML model may output recommendations for how to reprogram parameters of the IMD, such as how to reprogram sensitivity threshold utilized in connection with identifying P waves, R waves and T waves
this is not the same as the limitation as claimed. The specification does not disclose the IMD memory storing the adjustment to reprogram the sensing parameter to reduce the number of false positive candidate arrhythmias episodes declared by the IMD. This limitation is neither recited in the originally filed claims, shown in the originally filed drawings, or disclosed in the originally filed specification. Therefore, it is new matter and fails to comply with the written description requirement.
Claim 39(ii) recites “wherein the external device is configured to transmit, to the IMD, an adjustment of the sensing parameter for the IMD.” While the specification discloses:
¶59-the external device 154 is in place to receive or transmit data to the microcontroller 121 through the telemetry circuits 164;
¶106-additionally or alternatively, the information may include observations or recommendations regarding potential adjustments that may be made to the parameters of the IMD to reduce the number of false positives
This is not the same as the limitations as claimed. The specification does not disclose the external device configured to transmit, to the IMD, an adjustment of the sensing parameter for the IMD, This limitation is neither recited in the originally filed claims, shown in the originally filed drawings, or disclosed in the originally filed specification. Therefore, it is new matter and fails to comply with the written description requirement.
Claim 40 recites “wherein the IMD is further configured to adjust the sensing parameter based on the adjustment to reduce a number of false positive candidate arrhythmia episodes declared by the IMD.” While the specification discloses:
¶106-additionally or alternatively, the information may include observations or recommendations regarding potential adjustments that may be made to the parameters of the IMD to reduce the number of false positives, additionally or alternatively, the ML model may output recommendations for how to reprogram parameters of the IMD, such as how to reprogram sensitivity threshold utilized in connection with identifying P waves, R waves and T waves.
This is not the same as the limitations as claimed. The specification does not disclose wherein the IMD is further configured to adjust the sensing parameter based on the adjustment to reduce a number of false positive candidate arrhythmia episodes declared by the IMD. A recommendation for an adjustment is not the same as performing an adjustment. This limitation is neither recited in the originally filed claims, shown in the originally filed drawings, or disclosed in the originally filed specification. Therefore, it is new matter and fails to comply with the written description requirement.
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, 36, and 39-40 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.
Claims 5, 36, and 39 recite the limitation "the sensing parameter." There is insufficient antecedent basis for this limitation in the claim. For the purpose of examination, the Examiner is interpreting the limitation as “a sensing parameter.” Dependent claim 40 is rejected for the same deficiency as claim 39.
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, 26-31, 33-34, 36-37, 39(i), and 39(ii) are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception, specifically an abstract idea.
Step 1
The claimed invention in claims 1-3, 5-7, 26-31, 33-34, 36-37, 39(i), and 39(ii) are directed to statutory subject matter as the claims recite a system for declaring arrhythmias in cardiac activity.
Step 2A, Prong One
Regarding claim 1, the recited steps are directed to a mental process of performing concepts in a human mind or by a human using a pen and paper (see MPEP 2106.04(a)(2) subsection (III)).
Regarding claim 1, the limitations of “obtain device classified arrhythmia (DCA) data sets …for corresponding candidate arrhythmia episodes, the DCA data sets including the CA signals for one or more beats sensed by the IMD and one or more device documented (DD) markers that are generated by the IMD; identify a valid sub-set of the DCA data sets that correctly characterize the corresponding CA signals and to identify an invalid sub-set of the DCA data sets that incorrectly characterize the corresponding CA signals; i) a confidence indicator indicative of a degree of confidence that the corresponding DCA data set represents a true positive or false positive designation of an arrhythmia of interest; ii) a confidence indicator indicative of an accuracy of R-wave sensing implemented by the IMD; iii) a recommendation indicative of a sensitivity level to be utilized by the IMD to identify R waves in the CA signals; or iv) an output indicating that a particular DCA data set is unduly noisy and should not be characterized as a normal sinus rhythm, nor an arrhythmia, wherein an unduly noisy DCA data set is determined using a threshold; and present the output…as information concerning at least one of the valid sub-set or invalid sub-set of the DCA data sets” are a process, as drafted, covers performance of the limitation that can be performed by a human mind (including an observation, evaluation, judgment, opinion) under the broadest reasonable standard. For example, these limitations are nothing more than a medical professional receiving a paper print out of DCA data sets for corresponding candidate arrhythmia episodes, the DCA data sets including the CA signals for one or more beats sensed by the IMD and one or more device documented (DD) markers that are generated by the IMD, identifying a valid sub-set of the DCA data sets that correctly characterize the corresponding CA signals and to identifying an invalid sub-set of the DCA data sets that incorrectly characterize the corresponding CA signals, further analyzing a confidence indicator indicative of a degree of confidence that the corresponding DCA data set represents a true positive or false positive designation of an arrhythmia of interest, analyzing a confidence indicator indicative of an accuracy of R-wave sensing implemented by the IMD; writing down a recommendation indicative of a sensitivity level to be utilized by the IMD to identify R waves in the CA signals; or indicating that a particular DCA data set is unduly noisy and should not be characterized as a normal sinus rhythm, nor an arrhythmia, wherein an unduly noisy DCA data set is determined using a threshold. In addition, the medical professional writes down the information concerning at least one of the valid sub-set or invalid sub-set of the DCA data sets.
Step 2A, Prong Two
For claim 1, the judicial exception is not integrated into a practical application. In particular, claim 1 recites “an implantable medical device (IMD) configured to collect cardiac activity (CA) signals and to declare candidate arrhythmia episodes; an external device; memory; one or more processors; and a display.” The implantable medical device (IMD) amounts to nothing more than pre-solution activity of data gathering. The external device, memory, one or more processors, and display are recited at a high-level of generality and amount to nothing more than parts of a generic computer. Using the display to present additionally amounts to post-solution activity. Additionally, Applicant includes a machine learning (ML) model which is nothing more than the computer implementation/automation of an abstract mental process of screening a patient, which is what a physician typically does with a patient in a diagnostic setting. Merely including instructions to implement an abstract idea on a computer does not integrate a judicial exception into practical application.
Step 2B
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into
a practical application, the additional element of an implantable medical device (IMD) amounts to nothing more than mere pre-solution activity of data gathering, which does not amount to an inventive concept. Moreover, the IMD is recited at a high level of generality and are well-understood, routine, and conventional structures as evidenced by US 20200214576 (¶55-an implantable medical device known in the art), US 20200077940 (¶62-an implantable medical device known in the art), and US 20200029812 (¶4-various sorts of implantable monitoring devices are known in the art. (“Implantable” in this context includes devices that are inserted under the patient's skin, as well as deeper inside the body)). Further, simply appending well-understood, routine, conventional activities previously known to the industry, specified at a high level of generality, to the judicial exception, e.g., a claim to an abstract idea requiring no more than a generic computer to perform generic computer functions that are well-understood, routine and conventional activities previously known to the industry, as discussed in Alice Corp., 573 U.S. at 225, 110 USPQ2d at 1984 (see MPEP § 2106.05(d)).
Regarding dependent claims 2-3, 5-7, 26-31, 33-34, 36-37, 39(i), and 39(ii), the limitations of claim 1 further define the limitations already indicated as being directed to the abstract idea.
Claim 2 further includes details about the ML model. A machine learning (ML) model is nothing more than the computer implementation/automation of an abstract mental process of screening a patient, which is what a physician typically does with a patient in a diagnostic setting.
Regarding claim 3, a machine learning (ML) model is nothing more than the computer implementation/automation of an abstract mental process of screening a patient, which is what a physician typically does with a patient in a diagnostic setting. The limitations of “identify one or more features of interest based in part on the CA signals aligned in time with the corresponding DD markers, and identify the invalid sub-set of the DCA data sets” are a process, as drafted, covers performance of the limitation that can be performed by a human mind (including an observation, evaluation, judgment, opinion) under the broadest reasonable standard. For example, these limitations are nothing more than a medical professional analyzing print outs of CA signals and DD markers to identify one or more features of interest based in part on the CA signals aligned in time with the corresponding DD markers, and identify the invalid sub-set of the DCA data sets.
Regarding claim 5, the subcutaneous electrodes amount to pre-solution activity of data gathering. Subcutaneous electrodes are recited at a high level of generality and are well-understood, routine, and conventional structures as evidenced by US 11679265 (col. 4 and lines 41-45-the IMD 16 may be any suitable device known to one of ordinary skill in the art having the benefit of this disclosure that can operably couple to one or more implantable leads and one or more electrodes to sense electrical activity or to deliver therapy), US 20200337563 (¶40-a more conventional type of pacemaker and/or ICD that includes a housing implanted in a pectoral region with leads having electrodes implanted within a patient's heart), and US 20190126054 (¶3-implantable systems are known for cardiac stimulation and for cardioversion and defibrillation (implantable cardioverter-defibrillators, ICDs) that consist of an implant housing and that comprise energy supply, capacitors, electronics modules, etc., and one or more electrode leads. The electrode leads have one or more electrodes for measuring cardiac potentials and/or outputting stimulation pulses). The memory and one or more processors are recited at a high-level of generality and amount to nothing more than parts of a generic computer. The transceiver amounts to post-solution activity. The limitations of “analyze the CA signals, utilizing the sensing parameter, and based on the analysis declare the candidate arrhythmia episodes; and generate the DCA data sets including the corresponding CA signals and the corresponding DD markers” are a process, as drafted, covers performance of the limitation that can be performed by a human mind (including an observation, evaluation, judgment, opinion) under the broadest reasonable standard. For example, these limitations are nothing more than a medical professional analyzing print outs of CA signals and based on the analysis declare the candidate arrhythmia episodes; and writing down the DCA data sets including the corresponding CA signals and the corresponding DD markers.
Regarding claim 6, the external device/local external device, memory, and one or more processors are recited at a high-level of generality and amount to nothing more than parts of a generic computer. The transceiver amounts to post-solution activity.
Regarding claim 7, the external device, server, memory, and one or more processors are recited at a high-level of generality and amount to nothing more than parts of a generic computer. A machine learning (ML) model is nothing more than the computer implementation/automation of an abstract mental process of screening a patient, which is what a physician typically does with a patient in a diagnostic setting.
Regarding claim 26, a machine learning (ML) model is nothing more than the computer implementation/automation of an abstract mental process of screening a patient, which is what a physician typically does with a patient in a diagnostic setting. The limitations of “outputs, in connection with each of a plurality of the DCA data sets, the confidence indicator indicative of a degree of confidence that the corresponding DCA data set represents a true positive or false positive designation of an arrhythmia of interest, the confidence indicator representing at least a portion of the information displayed” are a process, as drafted, covers performance of the limitation that can be performed by a human mind (including an observation, evaluation, judgment, opinion) under the broadest reasonable standard. For example, these limitations are nothing more than a medical professional writing down a confidence indicator for each of the DCA data sets.
Regarding claim 27, the limitations of “compare the confidence indicators for the corresponding DCA data sets to a detection threshold; and add the corresponding DCA data set to the valid sub-set or invalid sub-set based on the comparison” are a process, as drafted, covers performance of the limitation that can be performed by a human mind (including an observation, evaluation, judgment, opinion) under the broadest reasonable standard. For example, these limitations are nothing more than a medical professional performing a simple threshold comparison and adding the corresponding DCA data set to the valid sub-set or invalid sub-set based on the comparison.
Regarding claim 28, a machine learning (ML) model is nothing more than the computer implementation/automation of an abstract mental process of screening a patient, which is what a physician typically does with a patient in a diagnostic setting. The limitations of “configured to adjust the detection threshold, utilized in connection with identifying at least one of P waves, R waves and T waves in the DCA data sets” are a process, as drafted, covers performance of the limitation that can be performed by a human mind (including an observation, evaluation, judgment, opinion) under the broadest reasonable standard. For example, these limitations are nothing more than a medical professional changing a threshold and identifying at least one of P waves, R waves and T waves in the DCA data sets.
Regarding claim 29, a machine learning (ML) model is nothing more than the computer implementation/automation of an abstract mental process of screening a patient, which is what a physician typically does with a patient in a diagnostic setting. The limitations of “wherein, in response to the confidence indicator indicating a high confidence of the true positive designation…decrease a detection threshold…in connection with identifying at least one of P waves, R waves and T waves in the DCA data sets” are a process, as drafted, covers performance of the limitation that can be performed by a human mind (including an observation, evaluation, judgment, opinion) under the broadest reasonable standard. For example, these limitations are nothing more than a medical professional decreasing a threshold value when the confidence indicator indicates a high confidence and analyzing at least one of P waves, R waves and T waves in the DCA data sets.
Regarding claim 30, recites further details regarding the machine learning model. C machine learning (ML) model is nothing more than the computer implementation/automation of an abstract mental process of screening a patient, which is what a physician typically does with a patient in a diagnostic setting.
Regarding claim 31, the display is recited at a high-level of generality and amounts to nothing more than a part of a generic computer. Using the display to present additionally amounts to post-solution activity.
Regarding claim 33, a machine learning (ML) model is nothing more than the computer implementation/automation of an abstract mental process of screening a patient, which is what a physician typically does with a patient in a diagnostic setting. The limitation of “output an alert to recommend reprogramming the IMD” is a process, as drafted, covers performance of the limitation that are directed to organizing human activity (managing personal behavior or relationships or interactions between people including social activities, teaching, and following rules or instructions). For example, this limitation is nothing more than a medical professional verbally communicating about reprogramming the IMD.
Regarding claim 34, a machine learning (ML) model is nothing more than the computer implementation/automation of an abstract mental process of screening a patient, which is what a physician typically does with a patient in a diagnostic setting. The limitation of “recommendations for how to reprogram a sensitivity threshold utilized in connection with identifying at least one of i) P waves, ii) R waves, or T waves to avoid over sensing or under sensing of i) P waves, ii) R waves, or T waves” is a process, as drafted, covers performance of the limitation that can be performed by a human mind (including an observation, evaluation, judgment, opinion) under the broadest reasonable standard. For example, this limitation is nothing more than a medical professional writing down a new sensitivity threshold based on analyzing at least one of P waves, R waves, or T waves.
Regarding claim 36, the memory is recited at a high-level of generality and amounts to nothing more than a part of a generic computer.
Regarding claim 37, a machine learning (ML) model is nothing more than the computer implementation/automation of an abstract mental process of screening a patient, which is what a physician typically does with a patient in a diagnostic setting. The limitations of “analyze the DCA data sets, based on a first threshold, to extract one or more features of interest from each of the DCA data sets, receive a clinician input to adjust the first threshold to a second threshold; and repeat the analyze and apply operations utilizing the second threshold…reclassifies a portion of the invalid sub-set of the DCA data sets, wherein the information displayed relates to the portion reclassified” are a process, as drafted, covers performance of the limitation that can be performed by a human mind (including an observation, evaluation, judgment, opinion) under the broadest reasonable standard. For example, these limitations are nothing more than a medical professional analyzing print outs of DCA data sets, performing threshold comparisons to extract features, changing the first threshold to a second threshold, and repeating to reclassify the invalid sub-set of the DCA data sets. The displaying amounts to post-solution activity.
Regarding claim 39(i), a machine learning (ML) model is nothing more than the computer implementation/automation of an abstract mental process of screening a patient, which is what a physician typically does with a patient in a diagnostic setting. The limitation of “a recommendation indicative of a sensitivity level to be utilized by the IMD to identify R waves in the CA signals” isa process, as drafted, covers performance of the limitation that can be performed by a human mind (including an observation, evaluation, judgment, opinion) under the broadest reasonable standard. For example, this limitation is nothing more than a medical professional writing down a new sensitivity level to identify R waves in CA signals based on analysis.
Regarding claim 39(ii), the transmission from the external device amounts to post-solution activity.
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1, 6-7, 26, 36, 39(ii), and 40 are rejected under 35 U.S.C. 103 as being unpatentable over Dani (US 20200357519 filed on 4/17/20) in view of Perschbacher (US 20170290550 filed on 4/4/17), hereinafter referred to as Persch.
Regarding claim 1, Dani teaches a system for declaring arrhythmias in cardiac activity, comprising: an implantable medical device (IMD) configured to collect cardiac activity (CA) signals (¶9-an IMD, senses cardiac electrogram data of a patient) and to declare candidate arrhythmia episodes (¶7-detecting or classifying an episode cardiac arrhythmia); and an external device (¶29-external device 12) comprising: memory (¶34-memory) to store specific executable instructions (¶44-instructions from external device 12) and a machine learning (ML) model (¶37-a machine learning model); one or more processors (¶31-a processor) configured to execute the specific executable instructions to: obtain device classified arrhythmia (DCA) data sets generated by the IMD for corresponding candidate arrhythmia episodes declared by the IMD (¶37-a medical device, such as IMD 10…uses feature delineation to make a preliminary detection of cardiac arrhythmia in patient 4), the DCA data sets including the CA signals for one or more beats sensed by the IMD (¶9-a medical device, such as an IMD, senses cardiac electrogram data of a patient. The medical device performs feature-based delineation of the cardiac electrogram data to obtain cardiac features indicative of an episode of arrhythmia in the patient) and one or more device documented (DD) markers that are generated by the IMD (¶65-IMD 10 further applies feature delineation to the cardiac electrogram data to detect one or more episodes of arrhythmia. For example, IMD 10 may apply QRS detection delineation and noise flagging to the cardiac electrogram data to provide arrhythmia characteristics and/or cardiac features for detected episodes of arrhythmia); and apply the ML model to the DCA data sets to identify a valid sub-set of the DCA data sets that correctly characterize the corresponding CA signals (¶37-verify that feature delineation of the cardiac electrogram data has correctly detected an episode of cardiac arrhythmia. In some examples, the medical device applies a machine learning model to cardiac electrogram data of patient 2 to verify that feature delineation of the cardiac electrogram data has correctly classified an episode of cardiac arrhythmia as a particular type of arrhythmia) and to identify an invalid sub-set of the DCA data sets that incorrectly characterize the corresponding CA signals (¶90-feature delineation incorrectly determines that an episode of cardiac arrhythmia has occurred in patient 4); and a display configured to present the output of the ML model as information concerning at least one of the valid sub-set or invalid sub-set of the DCA data sets (¶8-use of a machine learning model, such as a neural network or deep-learning model, that is trained on training datasets to detect cardiac arrhythmia from cardiac electrogram data; ¶104-outputting, by the medical device and for display, the report comprising the indication that the episode of arrhythmia has occurred in the patient and the one or more of the cardiac features that coincide with the episode of arrhythmia). However, Dani does not explicitly teach i) a confidence indicator indicative of a degree of confidence that the corresponding DCA data set represents a true positive or false positive designation of an arrhythmia of interest.
Persch relates generally to detecting and managing cardiac arrhythmias (¶2). Persch further teaches the confidence-based arrhythmia detector as being implemented in the IMD (¶50). Additionally,
Persch teaches the confidence-based arrhythmia detection using first and second detection processes
may also enhance the performance and functionality of an implantable CRM device, in certain examples,
increasing the specificity of existing arrhythmia detection (e.g., reducing false positives), such that
system performance can be improved with little to no additional cost, while reducing costs associated
with false detections, or manual inspection required by such false determinations (¶32). Persch further teaches the invention using the following step:
i) a confidence indicator indicative of a degree of confidence that the corresponding DCA data set (¶8-a confidence indicator indicating a confidence level of the detection of the arrhythmic event) represents a true positive or false positive designation of an arrhythmia of interest (¶32-confidence-based arrhythmia detection, false positive, false determinations).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Dani to include i) a confidence indicator indicative of a degree of confidence that the corresponding DCA data set represents a true positive or false positive designation of an arrhythmia of interest of Persch in order for detecting and managing cardiac arrhythmias (Persch, ¶2).
Regarding claim 6, the combination of Dani and Persch teaches the system of claim 1, wherein the external device represents a local external device that includes the memory and the one or more processors and a transceiver (Dani, ¶47-external device 12 , or by using another local or networked computing device configured to communicate with processing circuitry 50 via communication circuitry 54; ¶29-wireless telemetry; ¶34-memory), the transceiver configured to wirelessly receive the DCA data sets from the IMD (Dani, ¶29-external device 12 may be a computing device configured for use in settings such as a home, clinic, or hospital, and may further be configured to communicate with IMD 10 via wireless telemetry; ¶34).
Regarding claim 7, the combination of Dani and Persch teaches the system of claim 1, wherein the external device represents a server that includes the memory and the one or more processors (Dani, ¶36-transmit the signals from the electrodes or other sensors to another device (e.g., external device 12 ) or server; ¶34-memory; ¶31-processor), the memory configured to store the collection of the DCA data sets (Dani, ¶34), the one or more processors configured to apply the ML model to the collection of the DCA data sets (Dani, ¶12-applying, by the medical device, the machine learning model, trained using cardiac electrogram data for a plurality of patients, to the sensed cardiac electrogram data to verify, based on the machine learning model, that the episode of arrhythmia has occurred in the patient).
Regarding claim 26, the combination of Dani and Persch teaches the system of claim 1, wherein the ML model outputs, in connection with each of a plurality of the DCA data sets (Dani, ¶8-use of a machine learning model, such as a neural network or deep-learning model, that is trained on training datasets to detect cardiac arrhythmia from cardiac electrogram data), the confidence indicator indicative of a degree of confidence that the corresponding DCA data set (Persch, ¶8-a confidence indicator indicating a confidence level of the detection of the arrhythmic event) represents a true positive or false positive designation of an arrhythmia of interest (Persch, ¶32-confidence-based arrhythmia detection, false positive, false determinations), the confidence indicator representing at least a portion of the information displayed (Persch, ¶70-the output module 252 may include a display for displaying the information. The information may be presented in a table, a chart, a diagram, or any other types of textual, tabular, or graphical presentation formats, for displaying to a system user; ¶50).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Dani to include the confidence indicator indicative of a degree of confidence that the corresponding DCA data set represents a true positive or false positive designation of an arrhythmia of interest, the confidence indicator representing at least a portion of the information displayed of Persch in order for detecting and managing cardiac arrhythmias (Persch, ¶2).
Regarding claim 36, the combination of Dani and Persch teaches the system of claim 1, wherein the IMD comprises IMD memory configured to store the adjustments to reprogram the sensing parameter to reduce the number of false positive candidate arrhythmias episodes declared by the IMD (Dani, ¶34-external device 12 may be used to interrogate IMD 10 to retrieve data, including device operational data as well as physiological data accumulated in IMD memory; ¶30-program IMD 10 , e.g., select or adjust values for operational parameters of IMD 10).
Regarding claim 39(ii), the combination of Dani and Persch teaches the system of claim 1, wherein the external device is configured to transmit, to the IMD, an adjustment of the sensing parameter for the IMD (Dani, ¶44-inputs a command to external device 12 instructing IMD 10 to upload the cardiac electrogram data for analysis by a monitoring center or clinician; ¶30-interact with external device 12 to program IMD 10, e.g., select or adjust values for operational parameters of IMD 10).
Regarding claim 40, the combination of Dani and Persch teaches the system of claim 39(ii), wherein the IMD is further configured to adjust the sensing parameter based on the adjustment to reduce a number of false positive candidate arrhythmia episodes declared by the IMD (Dani, ¶74-IMD 10 perform such adjustments to for subsequent sensing of the cardiac electrogram data of patient 4; ¶77-avoid using the machine learning model to verify that an episode of arrhythmia was correctly detected by feature delineation where the episode of arrhythmia is likely to be falsely triggered).
Claim 2 is rejected under 35 U.S.C. 103 as being unpatentable over Dani in view of Persch as applied to claim 1 above, and further in view of Lu (US 20200178825 filed on 12/5/18).
Regarding claim 2, the combination of Dani and Persch teaches the system of claim 1. However, the combination of Dani and Persch does not teach wherein the ML model represents a convolutional neural network comprising sub-layers and including one or more rectified linear unit activation functions and batch normalization.
Lu teaches wherein the ML model represents a convolutional neural network (¶30-convolutional neural network (CNN)) comprising sub-layers (¶30-include one or more additional convolutional layers)
and including one or more rectified linear unit activation functions (101 in Fig. 6 and ¶35-activation function of leaky relu) and batch normalization (101 in Fig. 6 and ¶35-batch normalization).
Lu relates generally to cardiac monitoring, such as electrocardiography, and more particularly,
to automatic detection of cardiac abnormalities from cardiac waveforms with deep neural networks
(¶1). Lu further teaches the use of batch normalization and an activation function of leaky relu in the
first layer of the convolutional neural network (¶35). A novel deep neural network system and training
structure of Lu requires minimal pre-processing of ECG waveforms and does not require feature
extraction or waveform parameter identification prior to providing the ECG data to the neural network
system (¶17).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Dani to include wherein the ML model represents a convolutional neural network comprising sub-layers and including one or more rectified linear unit activation functions and batch normalization of Lu in order to identify arrhythmias based on cardiac waveforms while minimizing pre-processing of ECG waveforms (Lu, ¶17).
Claims 3, 5, and 31 are rejected under 35 U.S.C. 103 as being unpatentable over Dani in view of Persch as applied to claim 1 above, and further in view of Pedalty (US 20200352462 filed on 4/16/20).
Regarding claim 3, Dani teaches the system of claim 1, wherein the CA signals represent subcutaneous electrocardiogram (EGM) signals for a series of beats over a predetermined period of time (¶27-IMD 10 may be implanted outside of a thoracic cavity of patient 4 (e.g., subcutaneously in the pectoral location illustrated in FIG. 1); ¶50-an electrocardiogram of patient 4; ¶50-analyzes patient data that represents one or more values that are averaged over a short-term period of time (e.g., about 3 minutes)), and the ML model applied to the one or more features of interest for the DCA data sets to identify the invalid sub-set of the DCA data sets (¶37-applies a machine learning model to cardiac electrogram data of patient 2 to verify that feature delineation of the cardiac electrogram data has correctly detected an episode of cardiac arrhythmia). However, the combination of Dani and Persch does not teach wherein the one or more processors configured to identify one or more features of interest based in part on the CA signals aligned in time with the corresponding DD markers.
Pedalty teaches the one or more processors configured to identify one or more features of interest based in part on the CA signals aligned in time with the corresponding DD markers (¶70-each ECG waveform is labeled with one or more episodes of arrhythmia of one or more types. For example, a training ECG waveform may include a plurality of segments, each segment labeled with a descriptor that specifies an absence of arrhythmia or a presence of an arrythmia of a particular classification (e.g., bradycardia, tachycardia, atrial fibrillation, ventricular fibrillation, or AV Block)).
Pedalty relates to medical devices (¶2).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Dani to include wherein the one or more processors configured to identify one or more features of interest based in part on the CA signals aligned in time with the corresponding DD markers of Pedalty in order for detecting or classifying cardiac arrhythmia in new cardiac electrogram data (Pedalty, ¶70).
Regarding claim 5, Dani teaches the system of claim 1, the IMD comprising: a combination of subcutaneous electrodes configured to collect the CA signals (¶27-IMD 10 may be implanted outside of a thoracic cavity of patient 4 (e.g., subcutaneously in the pectoral location illustrated in FIG. 1); ¶36-one or more sensors (e.g., electrodes) are described herein as being positioned on a housing of IMD 10); IMD memory (memory 56 in Fig. 2) configured to store program instructions; and one or more IMD processors (¶43-processing circuitry 50 may include any one or more of a microprocessor) configured to execute the program instructions to: analyze the CA signals, utilizing the sensing parameter, and based on the analysis declare the candidate arrhythmia episodes (¶11-analysis of cardiac features that have been identified by feature delineation as likely presenting an episode of arrhythmia in the patient); and a transceiver configured to wirelessly transmit the DCA data sets to the external device (¶29-external device 12 may be a computing device configured for use in settings such as a home, clinic, or hospital, and may further be configured to communicate with IMD 10 via wireless telemetry; ¶34; ¶37). However, the combination of Dani and Persch does not teach to generate the DCA data sets including the corresponding CA signals and the corresponding DD markers.
Pedalty teaches to generate the DCA data sets including the corresponding CA signals and the corresponding DD markers (¶70-each ECG waveform is labeled with one or more episodes of arrhythmia of one or more types. For example, a training ECG waveform may include a plurality of segments, each segment labeled with a descriptor that specifies an absence of arrhythmia or a presence of an arrythmia of a particular classification (e.g., bradycardia, tachycardia, atrial fibrillation, ventricular fibrillation, or AV Block)).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Dani to include generating the DCA data sets including the corresponding CA signals and the corresponding DD markers of Pedalty in order for detecting or classifying cardiac arrhythmia in new cardiac electrogram data (Pedalty, ¶70).
Regarding claim 31, the combination of Dani and Persch teaches the system of claim 1. However, the combination of Dani and Persch does not teach wherein the display is further configured to display the CA signals and corresponding DD markers from the valid sub-set.
Pedalty wherein the display is further configured to display the CA signals and corresponding DD markers from the valid sub-set (Fig. 10B- see 1020 which is an episode of arrhythmia in patient 4; Fig. 10C-display 1003 colors segments for which computing system 24 has determined a high likelihood that atrial fibrillation has occurred in patient 4 in green ( 1012 ), segments for which computing system 24 has made an uncertain determination of whether atrial fibrillation has occurred in patient 4 in yellow ( 1014 ), and segments for which computing system 24 has determined a low likelihood that atrial fibrillation has occurred in patient 4 in red ( 1016 ); Fig. 10D; ¶118-121).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Dani to include wherein the display is further configured to display the CA signals and corresponding DD markers from the valid sub-set of Pedalty in order to provide clear explainability and simple arrhythmia visualization of a machine learning system (Pedalty, ¶28).
Claim 27 is rejected under 35 U.S.C. 103 as being unpatentable over Dani in view of Persch as applied to claim 26 above, and further in view of Nakar (US 20180042510 filed on 7/11/17).
Regarding claim 27, the combination of Dani and Persch teaches the system of claim 26, wherein the one or more processors are further configured to: compare the confidence indicators for the corresponding DCA data sets to a detection threshold (Persch, ¶64-generate the confidence indicator based on a comparison of the signal metrics 222 and one or more thresholds).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Dani to include wherein the one or more processors are further configured to: compare the confidence indicators for the corresponding DCA data sets to a detection threshold of Persch in order for detecting and managing cardiac arrhythmias (Persch, ¶2).
However, the combination of Dani and Persch does not teach to add the corresponding DCA data set to the valid sub-set or invalid sub-set based on the comparison.
Nakar teaches to add the corresponding DCA data set to the valid sub-set or invalid sub-set based on the comparison (¶75-add beat information, arrhythmia, comparison).
Nakar relates generally to electrocardiograph (ECG) signals, and specifically to detecting ECG
signals having similar morphologies (¶2). Nakar further teaches a comparison to a threshold value (¶75).
If the comparison returns positive, the beat is assumed to represent the same arrhythmia as the
morphology pattern. In this case processor 40 may add this beat information into collective information
of map 82 of the heart (¶75).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Dani to include adding the corresponding DCA data set to the valid sub-set or invalid sub-set based on the comparison of Nakar in order to detect ECG signals having similar morphologies (Nakar, ¶2).
Claims 28-29 are rejected under 35 U.S.C. 103 as being unpatentable over Dani in view of Persch as applied to claims 1 and 26 above, and further in view of An (US 20130116578 filed on 12/26/12).
Regarding claim 28, the combination of Dani and Persch teaches the system of claim 1. However, the combination of Dani and Persch does not teach wherein the one or more processors are further configured to adjust the detection threshold to increase or decrease a sensitivity of the ML model utilized in connection with identifying at least one of P waves, R waves and T waves in the DCA data sets.
An teaches wherein the one or more processors are further configured to adjust the detection threshold to increase or decrease a sensitivity of the ML model utilized in connection with identifying at least one of P waves, R waves and T waves in the DCA data sets (¶56-a user may set the CAS threshold to some arbitrary high value and then dynamically or manually adjust the CAS threshold, such as to fine tune false positive or false negative rates (e.g., specificity or sensitivity); ¶174-a WHF detection algorithm include, but are not limited to, a neural network algorithm, a fuzzy logic algorithm, a linear regression model algorithm, a decision tree algorithm, a Hidden Markov Model algorithm, a k-nearest neighbor algorithm, and a support vector machine; ¶185-a measured increase in the Q-S1 time duration may indicate an increased risk of the subject experiencing a WHF event; ¶175-prediction by the WHF detection algorithm is adjusted according to the determined HF risk score. For example, detection thresholds may be adjusted to be more easily satisfied in order to increase the sensitivity of HF detection).
An relates generally to implantable medical devices, and more particularly, but not by way of limitation, to systems and methods for between-patient comparisons for risk stratification of future heart failure decompensation (¶3).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Dani to include wherein the one or more processors are further configured to adjust the detection threshold to increase or decrease a sensitivity of the ML model utilized in connection with identifying at least one of P waves, R waves and T waves in the DCA data sets of An in order to fine tune false positive or false negative rates (e.g., specificity or sensitivity) (An, ¶56).
Regarding claim 29, the combination of Dani and Persch teaches the system of claim 26, wherein, in response to the confidence indicator (Persch, ¶8-a confidence indicator indicating a confidence level of the detection of the arrhythmic event) indicating a high confidence (¶8-indicates a relatively high confidence).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Dani to include wherein, in response to the confidence indicator indicating a high confidence of Persch in order for detecting and managing cardiac arrhythmias (Persch, ¶2).
However, the combination of Dani and Persch does not teach the true positive designation, the one or more processors are further configured to decrease a detection threshold to increase a sensitivity of the ML model utilized in connection with identifying at least one of P waves, R waves and T waves in the DCA data sets.
An teaches the true positive designation (¶57-correctly characterizes more true positives), the one or more processors are further configured to decrease a detection threshold to increase a sensitivity of the ML model utilized in connection with identifying at least one of P waves, R waves and T waves in the DCA data sets (¶53-by increasing the sensitivity of these sensors (e.g., decreasing a threshold value); ¶185-a measured increase in the Q-S1 time duration may indicate an increased risk of the subject experiencing a WHF event; ¶175-prediction by the WHF detection algorithm is adjusted according to the determined HF risk score. For example, detection thresholds may be adjusted to be more easily satisfied in order to increase the sensitivity of HF detection; ¶174).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Dani to include the true positive designation, the one or more processors are further configured to decrease a detection threshold to increase a sensitivity of the ML model utilized in connection with identifying at least one of P waves, R waves and T waves in the DCA data sets of An in order to fine tune false positive or false negative rates (e.g., specificity or sensitivity) (An, ¶56).
Claim 30 is rejected under 35 U.S.C. 103 as being unpatentable over Dani in view of Persch as applied to claim 1 above, and further in view of Sirendi (US 20200008696 filed on 3/7/18).
Regarding claim 30, the combination of Dani and Persch teaches the system of claim 1. However, the combination of Dani and Persch does not teach wherein the ML model represents a model that is trained utilizing an augmented collection of DCA data sets, wherein the augmented collection of the DCA data sets includes reference DCA data sets from patients and synthetic DCA data sets that are generated based on the reference DCA data sets.
Sirendi teaches wherein the ML model represents a model that is trained utilizing an augmented collection of DCA data sets, wherein the augmented collection of the DCA data sets includes reference DCA data sets from patients (¶205-threshold values are determined based upon past data from multiple sources, for example a database containing physiological data for patients alongside occurrences of cardiac events may be used for training a classifier) and synthetic DCA data sets that are generated based on the reference DCA data sets (¶39; ¶42-Gaussian process, improved classifier; ¶139).
Sirendi relates to the analysis of cardiac data, in particular, the invention relates to a system and
method of determining the probability of a cardiac event occurring. This may enable timely preventative
action to be taken, or may enable the determination of periods where increased monitoring of a person
may be beneficial (¶1). Sirendi further teaches threshold values being determined based upon past data
from multiple sources, for example a database containing physiological data for patients alongside
occurrences of cardiac events may be used for training a classifier (¶199). Additionally, Sirendi teaches a
Gaussian process for training (¶139).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Dani to include wherein the ML model represents a model that is trained utilizing an augmented collection of DCA data sets, wherein the augmented collection of the DCA data sets includes reference DCA data sets from patients and synthetic DCA data sets that are generated based on the reference DCA data sets of Sirendi in order to determine the probability of a cardiac event occurring. This may enable timely preventative action to be taken, or may enable the determination of periods where increased monitoring of a person may be beneficial (Sirendi, ¶1).
Claim 33 is rejected under 35 U.S.C. 103 as being unpatentable over Dani in view of Persch as applied to claim 1 above, and further in view of Krause (US 20080300497 filed on 6/4/07).
Regarding claim 33, the combination of Dani and Persch teaches the system of claim 1. However, the combination of Dani and Persch does not teach wherein the ML model is further configured to output an alert to recommend reprogramming the IMD.
Krause teaches wherein the ML model is further configured to output an alert to recommend reprogramming the IMD (¶103-alert the physician that corrective action may be required, arrhythmia detection, reprograming, implanted device).
Krause relates generally to implantable medical devices (IMDs), and, more particularly, the present invention relates to detecting noisy physiologic data intervals (¶1). Krause additionally teaches to alert the physician that corrective action may be required in order to ensure proper sensing and arrhythmia detection. Such action may include reprogramming sensing or detection parameters or repositioning an electrode or an implanted device (¶103).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Dani to include wherein the ML model is further configured to output an alert to recommend reprogramming the IMD of Krause in order to ensure proper sensing and arrhythmia detection (Krause, ¶103).
Claim 34 is rejected under 35 U.S.C. 103 as being unpatentable over Dani in view of Persch as applied to claim 1 above, and further in view of Sarkar (US 20170273589 filed on 3/25/16).
Regarding claim 34, the combination of Dani and Persch teaches the system of claim 1. However, the combination of Dani and Persch does not teach wherein the ML model is further configured to output recommendations for how to reprogram a sensitivity threshold utilized in connection with identifying at least one of i) P waves, ii) R waves, or T waves to avoid over sensing or under sensing of i) P waves, ii) R waves, or T waves.
Sarkar teaches wherein the ML model is further configured to output recommendations for how to reprogram a sensitivity threshold utilized in connection with identifying at least one of i) P waves, ii) R waves, or T waves to avoid over sensing or under sensing of i) P waves, ii) R waves, or T waves (¶26-second auto-correct threshold to sense events under-sensed by the first channel, R-waves; ¶36-detect ventricular events (e.g., R-waves) under-sensed by the first ventricular sense amplifier 222; ¶53-one or more algorithms; ¶56-user interface that presents information; ¶54).
Sarkar relates generally to medical devices, and in particular to medical devices that sense a signal indicative of cardiac activity (¶1). Sarkar additionally relates to a determination being made whether the bradycardia or the asystole is false based on the detection of under-sensed events (¶5).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Dani to include wherein the adjustment reprograms a sensitivity threshold utilized in connection with identifying at least one of i) P waves, ii) R waves, or T waves to avoid over sensing or under sensing of i) P waves, ii) R waves, or T waves of Sarkar in order to detect various types of arrhythmias (Sarkar, ¶23) and making a determination about whether the bradycardia or the asystole is false based on the detection of under-sensed events (Sarkar, ¶5).
Claim 39(i) is rejected under 35 U.S.C. 103 as being unpatentable over Dani in view of Persch as applied to claim 1 above, and further in view of Dawoud (US 20190336026 published on 11/7/19).
Regarding claim 39(i), the combination of Dani and Persch teaches the system of claim 1. However, the combination of Dani and Persch does not teach wherein the output of the ML model represents a recommendation indicative of a sensitivity level to be utilized by the IMD to identify R waves in the CA signals.
Dawoud wherein the output of the ML model represents a recommendation indicative of a sensitivity level to be utilized by the IMD to identify R waves in the CA signals (¶34-developing recommendations for sensitivity profile parameter settings; ¶87-the confirmatory feature detection process 137 may implement one or more of the R-wave detection processes; ¶141-the sensitivity profile parameter adjustments, in the confirmation log, may be presented on a display; ¶160-CA signal, detection algorithm).
Dawoud relates generally to implantable medical devices, and more particularly to detection and discrimination of arrhythmic patterns of interest (¶6).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Dani to include wherein the output of the ML model represents a recommendation indicative of a sensitivity level to be utilized by the IMD to identify R waves in the CA signals of Dawoud in order to detect an arrhythmia within the beat segment of interest based on a presence or absence of the one or more R-waves (Dawoud, ¶14).
Examiner’s Note
Claim 37 distinguishes over the prior art but are still rejected under 35 USC § 101.
The following is a statement of reasons for the indication of overcoming the prior art:
The scope of wherein the one or more processors are further configured to: analyze the DCA data sets, based on a first threshold, to extract one or more features of interest from each of the DCA data sets, the ML model applied to the one or more features of interest for the DCA data sets; receive a clinician input to adjust the first threshold to a second threshold; and repeat the analyze and apply operations utilizing the second threshold such that the ML model reclassifies a portion of the invalid sub-set of the DCA data sets, wherein the information displayed relates to the portion reclassified recited in claims 37 and 38 were not found in the prior art alone or in combination with one another to be obvious over the prior art of record. The closest prior art of record is US 20200357519; however it fails to recite receiving a clinician input to adjust the first threshold to a second threshold; repeating the analyzing and applying operations utilizing the second threshold such that the ML model reclassifies a portion of the invalid sub-set of the DCA data sets, wherein the information displayed relates to the portion reclassified.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
US 20210345900: relate generally to implantable medical devices, and more particularly to detection of low-level P-waves and discrimination of noise in cardiac activity signals (¶1).
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 LAURA HODGE whose telephone number is (571) 272-7101. The examiner can normally be reached M-F: 8:00 am-5:00 pm.
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, UNSU JUNG can be reached at (571) 272-8506. 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.
/L.N.H./Examiner, Art Unit 3792
/AMANDA L STEINBERG/Examiner, Art Unit 3792
Prosecution Insights