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 .
Information Disclosure Statement
Applicant should note that the large number of references in the attached IDS, see IDS filed 1/27/2026, have been considered by the examiner in the same manner as other documents in Office search files are considered by the examiner while conducting a search of the prior art in a proper filed of search. See MPEP 609.05(b). Applicant is requested to point out any particular references in the IDS which they believe may be of particular relevance to the instant claimed invention in response to this Office Action.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claim(s) 23 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by US 2020/0155829 to Giftakis et al. (Giftakis) (cited by applicant).
In reference to at least claim 23
Giftakis discloses a method of detecting seizures in a mammal (e.g. abstract; para. 0036: Patient 12 ordinarily will be a human patient), the method comprising: stimulating, with a first set of electrodes In a brain of the mammal, a region of the brain (e.g. para. 0036: Patient 12 ordinarily will be a human patient; para. 0038: IMD 16 includes a therapy module that comprises a stimulation generator that generates and delivers electrical stimulation therapy to patient 12 via a subset of electrodes 24, 26 of leads 20A and 20B...electrodes 24, 26 of leads 20A, 20B are positioned to deliver electrical stimulation to a tissue site within brain 28, such as a deep brain site under the dura mater of brain 28 of patient 12); while stimulating the region of the brain, acquiring an electrical signal sensed by a second subset of electrodes in the brain (e.g. para. 0044: IMD 16 may determine impedance of tissue within brain 28 based on signals sensed via any suitable combination of electrodes 24, 26; para. 0096: As previously indicated, in some examples, processor 40 detects a seizure based on bioelectrical brain signals sensed by sensing module 46 via a subset of electrodes 24, 26); identifying values for a time parameter and a frequency parameter to be used in signal power calculations (e.g. para. 0070: During the course of evaluating patient 12, the clinician may determine, for example, that the bioelectrical brain signal characteristics (e.g., amplitude, slope, pattern [time parameters], frequency, or frequency band characteristics [frequency parameters]) indicate an onset of a target seizure for which therapy delivery is desired); segmenting the electrical signal into a plurality of time-segmented portions according to a value of the time parameter (e.g. paras. 0156-0157: FIG. 7 schematically illustrates bioelectrical brain signal 90 generated by sensing module 46 (FIG. 2) of IMD 16...processor 40 of IMD 16 detects a seizure based on bioelectrical brain signal 90 at times 94 and 96 [time-segmented portions]); for each time-segmented portion of the electrical signal: determining a power of the time-segmented portion of the electrical signal within a frequency band defined by a value of the frequency parameter (e.g. para. 0143: processor 40 determines the one or more characteristics of the bioelectrical brain signal temporally correlating to the target seizure. The brain signal characteristics indicative of a seizure may include, for example, a mean, median, highest or lowest amplitude of a period of time preceding or overlapping with the time of occurrence of the target seizure, an instantaneous amplitude, one or more frequency band characteristics of the bioelectrical brain signal preceding or overlapping with the time of occurrence of the target seizure, or a signal template generated based on the bioelectrical brain signal sensed during the time period preceding the or overlapping with the time of occurrence of the target seizure); using a classifier to classify the time-segmented portion of the electrical signal as seizure positive or seizure negative based on the determined power (e.g. para. 0161: Processor 40 determines that for time period 96, brain signal 90 exhibited an average amplitude that is greater than threshold TH. Accordingly, processor 40 determines that during time period 96 [time segment], the target seizure detected based on patient activity signal 92 is a true seizure. On the other hand, processor 40 determines that for time period 98 [time segment], brain signal 90 exhibited normal behavior because an average amplitude of brain signal 90 during time period 98 was less than threshold TH) within the frequency band (e.g. para.0143: processor 40 determines the one or more characteristics of the bioelectrical brain signal temporally correlating to the target seizure. The brain signal characteristics indicative of a seizure may include, for example, a mean, median, highest or lowest amplitude of a period of time preceding or overlapping with the time of occurrence of the target seizure, an instantaneous amplitude, one or more frequency band characteristics of the bioelectrical brain signal preceding or overlapping with the time of occurrence of the target seizure, or a signal template generated based on the bioelectrical brain signal sensed during the time period preceding the or overlapping with the time of occurrence of the target seizure); and logging, in memory of a device implanted in the mammal (e.g. para. 0045: IMD 16 may comprise a hermetic outer housing 34 to substantially enclose components, such as a...memory), an indication of each seizure event detected in the mammal over a period of time, each seizure event corresponding to one or more time-segmented portions of the electrical signal that were classified as seizure positive (e.g. para. 0097: processor 40 detects a seizure by comparing an amplitude of a sensed bioelectrical brain signal to a threshold value that is stored as part of the seizure detection algorithm in memory 42; para. 0161: Processor 40 determines that for time period 96, brain signal 90 exhibited an average amplitude that is greater than threshold TH. Accordingly, processor 40 determines that during time period 96 [time segment], the target seizure detected based on patient activity signal 92 is a true seizure. On the other hand, processor 40 determines that for time period 98 [time segment], brain signal 90 exhibited normal behavior because an average amplitude of brain signal 90 during time period 98 was less than threshold TH).
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1-5,10-12,15, 18-19 and 24 is/are rejected under 35 U.S.C. 103 as being unpatentable over US 2020/0155829 to Giftakis et al. (herein Giftakis) in view of Expert-Level Intracranial Electroencephalogram Ictal Pattern Detection by a Deep Learning Neural Network to Constantino et al. (herein Constantino) (cited by applicant).
In reference to at least claim 1
Giftakis discloses a method of detecting seizures in a mammal (e.g. abstract; para. 0036: Patient 12 ordinarily will be a human patient), the method comprising: stimulating, with a first set of electrodes in a brain of the mammal, a region of the brain (e.g. para. 0036: Patient 12 ordinarily will be a human patient; para. 0038:IMD 16 includes a therapy module that comprises a stimulation generator that generates and delivers electrical stimulation therapy to patient 12 via a subset of electrodes 24,26 of leads 20A and 20B...electrodes 24,26 of leads 20A, 20B are positioned to deliver electrical stimulation to a tissue site within brain 28, such as a deep brain site under the dura mater of brain 28 of patient 12); while stimulating the region of the brain, acquiring an electrical signal sensed by a second subset of electrodes in the brain (e.g. para. 0044: IMD16 may determine impedance of tissue within brain 28 based on signals sensed via any suitable combination of electrodes 24,26. For example, as described in U.S. patent application Ser. No. 111799,051 to Denison et al., an impedance of brain 28 of patient 12 is measured by delivering a stimulation current to brain 28 via implanted electrodes; para. 0096: As previously indicated, in some examples, processor 40detects a seizure based on bioelectrical brain signals sensed by sensing module 46via a subset of electrodes 24, 26); identifying values for a time parameter and a frequency parameter to be used in signal power calculations (e.g. para. 0070: During the course of evaluating patient 12, the clinician may determine, for example, that the bioelectrical brain signal characteristics (e.g., amplitude, slope, pattern [time parameters], frequency, or frequency band characteristics [frequency parameters]) indicate an onset of a target seizure for which therapy delivery is desired); segmenting the electrical signal into a plurality of time-segmented portions according to a value of the time parameter (e.g. paras. 0156-0157: FIG. 7 schematically illustrates bioelectrical brain signal 90generated bysensingmodule46(FIG. 2) of IMD16...processor 40of IMD16detects a seizure based on bioelectrical brain signal 90at times94and96 [time-segmented portions]); for each time-segmented portion of the electrical signal: determining a power of the time-segmented portion of the electrical signal within a frequency band defined by a value of the frequency parameter (para. 0143: processor 40 determines the one or more characteristics of the bioelectrical brain signal temporally correlating to the target seizure. The brain signal characteristics indicative of a seizure may include, for example, a mean, median, highest or lowest amplitude of a period of time preceding or overlapping with the time of occurrence of the target seizure, an instantaneous amplitude, one or more frequency band characteristics of the bioelectrical brain signal preceding or overlapping with the time of occurrence of the target seizure, or a signal template generated based on the bioelectrical brain signal sensed during the time period preceding the or overlapping with the time of occurrence of the target seizure); and using a classifier to classify the time-segmented portion of the electrical signal as seizure positive or seizure negative based on the determined power (e.g. para. 0161: Processor 40 determines that for time period 96, brain signal 90exhibited an average amplitude that is greater than threshold TH. Accordingly, processor 40 determines that during time period 96 [time segment], the target seizure detected based on patient activity signal92is a true seizure. On the other hand, processor 40 determines that for time period 98 [time segment], brain signal 90exhibited normal behavior because an average amplitude of brain signal 90during time period 98 was less than threshold TH) within the frequency band (para. 0143: processor 40 determines the one or more characteristics of the bioelectrical brain signal temporally correlating to the target seizure. The brain signal characteristics indicative of a seizure may include, for example, a mean, median, highest or lowest amplitude of a period of time preceding or overlapping with the time of occurrence of the target seizure, an instantaneous amplitude, one or more frequency band characteristics of the bioelectrical brain signal preceding or overlapping with the time of occurrence of the target seizure, or a signal template generated based on the bioelectrical brain signal sensed during the time period preceding the or overlapping with the time of occurrence of the target seizure); wherein the values for the time parameter and the frequency parameter result in the classifier achieving an effective level of performance (e.g. para. 0068: Adjusting the seizure detection algorithm implemented by IMD 16 with the brain signal characteristics that are known to be associated with target seizures may help limit the number of false positive and false negative detections of target seizures by IMD 16 [effective performance]; para. 0143: processor 40 determines the one or more characteristics of the bioelectrical brain signal temporally correlating to the target seizure. The brain signal characteristics indicative of a seizure may include, for example, a mean, median, highest or lowest amplitude of a period of time preceding or overlapping with the time of occurrence of the target seizure, an instantaneous amplitude, one or more frequency band characteristics of the bioelectrical brain signal preceding or overlapping with the time of occurrence of the target seizure, or a signal template generated based on the bioelectrical brain signal sensed during the time period preceding the or overlapping with the time of occurrence of the target seizure).
Giftakis fails to explicitly disclose performance defined by an area under a precision-recall curve (AU-PRC) for the classifier of at least 0.5.
Constantino is in the field of EEG analysis systems (abstract/background) teaches performance defined by an area under a precision-recall curve (AU-PRC) for the classifier of at least 0.5 (e.g. Pg; 1 para. 3: Results: In scenario 1, the CNN achieved a maximum mean binary classification AUPRC of 0.84 ± 0.19 (95%CI, 0.72- 0.93) and mean regression accuracy of 6.3 ± 1.0 s (95%CI, 4.3- 8.5 s) at 30 seed samples).
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 method of Giftakis to include performance metrics being defined by an area under a precision-recall curve (AU-PRC) for the classifier of at least 0.5. as taught by Constantino in order to provide metrics that better analyze a system’s ability to detect seizures with high accuracy using a large dataset of expert-validated ictal patterns from the iEEG recordings of RNS-implanted epilepsy patients (Constantino, Pg. 5 para. 4).
In reference to at least claim 2
Giftakis modified by Constantino renders obvious a method according to claim 1. Giftakis further discloses wherein the mammal is a human (e.g. para. 0036: FIG. 1 is a conceptual diagram illustrating an example therapy system 10 that delivers therapy to manage a seizure disorder (e.g., epilepsy) of patient 12. Patient 12 ordinarily will be a human patient).
In reference to at least claim 3
Giftakis modified by Constantino renders obvious a method according to claim 1. Giftakis further discloses wherein the region of the brain stimulated with the first set of electrodes is a region of the thalamus (e.g. para. 0038: IMD16 includes a therapy module that comprises a stimulation generator that generates and delivers electrical stimulation therapy to patient 12 via a subset of electrodes 24, 26 of leads 20A and20B, respectively...ln some examples, delivery of stimulation to one or more regions of brain 28, such as...thalamus...of brain 28, may provide an effective treatment to manage a seizure disorder).
In reference to at least claim 4
Giftakis modified by Constantino renders obvious a method according to claim 3. Giftakis further discloses wherein the region of the brain stimulated with the first set of electrodes comprises an anterior nuclei of the thalamus (e.g. para. 0038: IMD 16 includes a therapy module that comprises a stimulation generator that generates and delivers electrical stimulation therapy to patient 12 via a subset of electrodes 24, 26 of leads 20A and 20B, respectively...ln some examples, delivery of stimulation to one or more regions of brain 28, such as anterior nucleus, thalamus...of brain 28, may provide an effective treatment to manage a seizure disorder).
In reference to at least claim 5
Giftakis modified by Constantino renders obvious a method according to claim 3. Giftakis further discloses wherein the second subset of electrodes produces the electrical signal responsive to brain activity (e.g. para. 0044: IMD 16 may determine impedance of tissue within brain 28 based on signals sensed via any suitable combination of electrodes 24,26. For example, as described in U.S. patent application Ser. No. 11/799,051 to Denison et al., an impedance of brain 28 of patient 12 is measured by delivering a stimulation current to brain 28 via implanted electrodes; para. 0096: As previously indicated, in some examples, processor 40 detects a seizure based on bioelectrical brain signals sensed by sensing module 46 via a subset of electrodes 24,26).
Giftakis fails to explicitly disclose brain activity in the hippocampus. Constantino teaches brain activity in the hippocampus (e.g. Pg. 2 para. 6: RNS leads were implanted as closely as possible to the recorded and/or hypothesis-derived epileptogenic regions (Supplementary Figure 1)...Patients with a diagnosis of mesio-temporal epilepsy were implanted with depth electrodes placed across the posterior anterior axis of the hippocampus).
It would have been obvious to one of ordinary skill in the art before the priority date to modify the method of Giftakis to include brain activity as taught by Constantino for the purpose of providing diagnoses and data analysis of said diagnoses across different parts of the brain using sensing electrodes (Constantino, Pg. 2 Para 6 - Pg. 3 para. 3).
In reference to at least claim 10
Giftakis modified by Constantino render obvious a method according to claim 1. Giftakis further discloses wherein stimulating the region of the brain comprises applying a chronic deep brain stimulation therapy to the region of the brain (e.g. para. 0038: electrodes 24, 26 of leads 20A, 20B are positioned to deliver electrical stimulation to a tissue site within brain 28, such as a deep brain site under the dura mater of brain 28 of patient 12; para. 0083: Therapy system 10 may be implemented to provide chronic stimulation therapy to patient 12 over the course of several months or years).
In reference to at least claim 11
Giftakis modified by Constantino renders obvious a method according to claim 1. Giftakis further discloses wherein the classifier is implemented on a device implanted in a body of the mammal (e.g. para. 0036: Patient 12 ordinarily will be a human patient; para. 0045: IMD16 may be implanted within a subcutaneous pocket above the clavicle, or, alternatively, the abdomen, back or buttocks of patient 12, on or within cranium 32 or at any other suitable site within patient 12; para. 0087: IMD16include...processor 40; para. 0161: Processor 40 determines that for time period 96, brain signal 90 exhibited an average amplitude that is greater than threshold TH. Accordingly, processor 40 determines that during time period 96, the target seizure detected based on patient activity signal 92 is a true seizure. On the other hand, processor 40 determines that for time period 98, brain signal 90 exhibited normal behavior because an average amplitude of brain signal 90 during time period 98 was less than threshold TH).
In reference to at least claim 12
Giftakis modified by Constantino renders obvious a method according to claim 11. Giftakis further discloses wherein the device includes a memory and is configured to maintain a log of seizures detected over time, wherein the device logs a seizure event in response to the classifier classifying one or more time-segmented portions of the electrical signal as seizure positive (e.g. para. 0097: processor 40 detects a seizure by comparing an amplitude of a sensed bioelectrical brain signal to a threshold value that is stored as part of the seizure detection algorithm in memory 42;para. 0161: Processor 40 determines that for time period 96, brain signal 90exhibited an average amplitude that is greater than threshold TH. Accordingly, processor 40 determines that during time period 96, the target seizure detected based on patient activity signal 92 is a true seizure. On the other hand, processor 40 determines that for time period 98, brain signal 90exhibited normal behavior because an average amplitude of brain signal 90 during time period 98 was less than threshold TH).
In reference to at least claim 15
Giftakis modified by Constantino renders obvious a method according to claim 11. Giftakis further discloses wherein the value for the time parameter is a temporal segment length that defines a temporal length of the time-segmented portions of the electrical signal (e.g. paras. 0156-0157: FIG. 7schematically illustrates bioelectrical brain signal 90 generated by sensing module 46 (FIG. 2) of IMD16...processor 40 of IMD16 detects a seizure based on bioelectrical brain signal 90 at times 94 and 96 [time-segmented portions, see Fig. 7 for temporal length]).
In reference to at least claim 18
Giftakis modified by Constantino renders obvious a method according to claim 1. Giftakis further discloses wherein using the classifier to classify the time-segmented portion of the electrical signal comprises comparing the determined power of the time-segmented portion of the electrical signal within the frequency band to a threshold power value (e.g. para. 0143: processor 40 determines the one or more characteristics of the bioelectrical brain signal temporally correlating to the target seizure. The brain signal characteristics indicative of a seizure may include, for example, a mean, median, highest or lowest amplitude of a period of time preceding or overlapping with the time of occurrence of the target seizure, an instantaneous amplitude, one or more frequency band characteristics of the bioelectrical brain signal preceding or overlapping with the time of occurrence of the target seizure, or a signal template generated based on the bioelectrical brain signal sensed during the time period preceding the or overlapping with the time of occurrence of the target seizure; para. 0161: Processor 40 determines that for time period 96, brain signal 90 exhibited an average amplitude that is greater than threshold TH. Accordingly, processor 40 determines that during time period 96 [time segment], the target seizure detected based on patient activity signal 92 is a true seizure. On the other hand, processor 40 determines that for time period 98 [time segment], brain signal 90 exhibited normal behavior because an average amplitude of brain signal 90 during time period 98 was less than threshold TH).
In reference to at least claim 19
Giftakis modified by Constantino renders obvious a method according to claim 1. Giftakis further discloses in response to detecting a seizure event based on identification of one or more seizure positive time-segmented portions of the electrical signal (e.g. para. 0161: Processor 40 determines that for time period 96, brain signal 90 exhibited an average amplitude that is greater than threshold TH. Accordingly, processor 40 determines that during time period 96 [time segment], the target seizure detected based on patient activity signal 92 is a true seizure. On the other hand, processor 40 determines that for time period 98 [time segment], brain signal 90 exhibited normal behavior because an average amplitude of brain signal 90 during time period 98 was less than threshold TH), adjusting one or more parameters by which the first set of electrodes stimulate the region of the brain (e.g. para. 0060: it may be desirable to deliver electrical stimulation to brain 28 of patient 12 upon detection of a sensory seizure; paras. 0072-0073: a signal generator within IMD 16 may generate the electrical stimulation therapy for DBS according to a therapy program that is selected at that given time in therapy...ln the example shown in FIG. 1, IMD 16 includes a memory to store a plurality of therapy programs that each defines a set of therapy parameter values [adjusted parameters]. In some examples, IMD 16 may select a therapy program from the memory based on various parameters, such as based on one or more characteristics of a bioelectrical brain signal).
In reference to at least claim 24
Giftakis discloses a system comprising circuitry (e.g. para. 0087: Processor 40 may include any one or more...application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), discrete logic circuitry) configured to perform a method of detecting seizures in a mammal (e.g. abstract; para. 0036: Patient 12 ordinarily will be a human patient), wherein the method comprises: stimulating, with a first set of electrodes in a brain of the mammal, a region of the brain (e.g. para. 0036: Patient 12 ordinarily will be a human patient; para. 0038: IMD16 includes a therapy module that comprises a stimulation generator that generates and delivers electrical stimulation therapy to patient 12 via a subset of electrodes 24,26 of leads 20A and 20B...electrodes 24,26 of leads 20A, 20B are positioned to deliver electrical stimulation to a tissue site within brain 28, such as a deep brain site under the dura mater of brain 28 of patient 12); while stimulating the region of the brain, acquiring an electrical signal sensed by a second subset of electrodes in the brain (e.g. para. 0044: IMD16 may determine impedance of tissue within brain 28 based on signals sensed via any suitable combination of electrodes 24,26. For example, as described in U.S. patent application Ser. No. 111799,051 to Denison et al., an impedance of brain 28 of patient 12 is measured by delivering a stimulation current to brain 28 via implanted electrodes; para. 0096: As previously indicated, in some examples, processor 40detects a seizure based on bioelectrical brain signals sensed bysensingmodule46via a subset of electrodes 24, 26); identifying values for a time parameter and a frequency parameter to be used in signal power calculations (e.g. para. 0070: During the course of evaluating patient 12, the clinician may determine, for example, that the bioelectrical brain signal characteristics (e.g., amplitude, slope, pattern [time parameters], frequency, or frequency band characteristics [frequency parameters]) indicate an onset of a target seizure for which therapy delivery is desired); segmenting the electrical signal into a plurality of time-segmented portions according to a value of the time parameter (e.g. paras. 0156-0157: FIG. 7 schematically illustrates bioelectrical brain signal 90generated bysensingmodule46(FIG. 2) of IMD16...processor 40of IMD16detects a seizure based on bioelectrical brain signal 90at times94and96 [time-segmented portions]); for each time-segmented portion of the electrical signal: determining a power of the time-segmented portion of the electrical signal within a frequency band defined by a value of the frequency parameter (para. 0143: processor 40 determines the one or more characteristics of the bioelectrical brain signal temporally correlating to the target seizure. The brain signal characteristics indicative of a seizure may include, for example, a mean, median, highest or lowest amplitude of a period of time preceding or overlapping with the time of occurrence of the target seizure, an instantaneous amplitude, one or more frequency band characteristics of the bioelectrical brain signal preceding or overlapping with the time of occurrence of the target seizure, or a signal template generated based on the bioelectrical brain signal sensed during the time period preceding the or overlapping with the time of occurrence of the target seizure); and using a classifier to classify the time-segmented portion of the electrical signal as seizure positive or seizure negative based on the determined power (e.g. para. 0161: Processor 40 determines that for time period 96, brain signal 90exhibited an average amplitude that is greater than threshold TH. Accordingly, processor 40 determines that during time period 96 [time segment], the target seizure detected based on patient activity signal92is a true seizure. On the other hand, processor 40 determines that for time period 98 [time segment], brain signal 90 exhibited normal behavior because an average amplitude of brain signal 90 during time period 98 was less than threshold TH) within the frequency band (para. 0143: processor 40 determines the one or more characteristics of the bioelectrical brain signal temporally correlating to the target seizure. The brain signal characteristics indicative of a seizure may include, for example, a mean, median, highest or lowest amplitude of a period of time preceding or overlapping with the time of occurrence of the target seizure, an instantaneous amplitude, one or more frequency band characteristics of the bioelectrical brain signal preceding or overlapping with the time of occurrence of the target seizure, or a signal template generated based on the bioelectrical brain signal sensed during the time period preceding the or overlapping with the time of occurrence of the target seizure); wherein the values for the time parameter and the frequency parameter result in the classifier achieving an effective level of performance (e.g. para. 0068: Adjusting the seizure detection algorithm implemented by IMD 16 with the brain signal characteristics that are known to be associated with target seizures may help limit the number of false positive and false negative detections of target seizures by IMD 16 [effective performance]; para. 0143: processor 40 determines the one or more characteristics of the bioelectrical brain signal temporally correlating to the target seizure. The brain signal characteristics indicative of a seizure may include, for example, a mean, median, highest or lowest amplitude of a period of time preceding or overlapping with the time of occurrence of the target seizure, an instantaneous amplitude, one or more frequency band characteristics of the bioelectrical brain signal preceding or overlapping with the time of occurrence of the target seizure, or a signal template generated based on the bioelectrical brain signal sensed during the time period preceding the or overlapping with the time of occurrence of the target seizure); (b) one or more stimulating electrodes disposed in a brain of a mammal; one or more sensing electrodes disposed in a brain of the mammal (e.g. electrodes 24, 26); a stimulation unit configured to generate and deliver stimulation signals to the stimulating electrodes to cause the stimulating electrodes to stimulate a region of a brain of the mammal (e.g. stimulation generator 44); a seizure detection unit (e.g. para. 0096: processor 40 detects seizure based on seizure detection algorithm 56), comprising: memory storing one or more sets of values for a time parameter and a frequency parameter (e.g. para. 0095-0096: memory 42 stores a seizure detection algorithm); signal acquisition circuitry (e.g. sensing module 46) configured to acquire an electroencephalogram (EEG) signal sensed by the one or more sensing electrodes (e.g. para. 0088: sensing module 46 senses bioelectrical brain signal via select combinations of electrodes); a signal segmentation engine configured to segment the EEG signal into a plurality of time-segmented portions according to a value of a time parameter (paras. 0156-0157: FIG. 7 schematically illustrates bioelectrical brain signal 90 generated by sensing module 46 (FIG. 2) of IMD 16...processor 40 of IMD 16 detects a seizure based on bioelectrical brain signal 90 at times 94 and 96 [time-segmented portions]); a power analyzer configured, for each time-segmented portion of the EEG signal, to determine a power of the time-segmented portion within a frequency band defined by a value of a frequency parameter (e.g. para. 0070: During the course of evaluating patient 12, the clinician may determine, for example, that the bioelectrical brain signal characteristics (e.g., amplitude, slope, pattern [time parameters], frequency, or frequency band characteristics [frequency parameters]); and a classifier configured, for each time-segmented portion of the EEG signal, to classify the time-segmented portion as seizure positive or seizure negative based on the determined power of the time-segmented power (e.g. para. 0161: Processor 40 determines that for time period 96, brain signal 90 exhibited an average amplitude that is greater than threshold TH. Accordingly, processor 40 determines that during time period 96 [time segment], the target seizure detected based on patient activity signal 92 is a true seizure. On the other hand, processor 40 determines that for time period 98 [time segment], brain signal 90 exhibited normal behavior because an average amplitude of brain signal 90 during time period 98 was less than threshold TH) within the frequency band (e.g. para.0143: processor 40 determines the one or more characteristics of the bioelectrical brain signal temporally correlating to the target seizure. The brain signal characteristics indicative of a seizure may include, for example, a mean, median, highest or lowest amplitude of a period of time preceding or overlapping with the time of occurrence of the target seizure, an instantaneous .amplitude, one or more frequency band characteristics of the bioelectrical brain signal preceding or overlapping with the time of occurrence of the target seizure, or a signal template generated based on the bioelectrical brain signal sensed during the time period preceding the or overlapping with the time of occurrence of the target seizure).
Giftakis fails to explicitly disclose performance defined by an area under a precision-recall curve (AU-PRC) for the classifier of at least 0.5.
Constantino is in the field of EEG analysis systems (abstract/background) teaches performance defined by an area under a precision-recall curve (AU-PRC) for the classifier of at least 0.5 (e.g. Pg; 1 para. 3: Results: In scenario 1, the CNN achieved a maximum mean binary classification AUPRC of 0.84 ± 0.19 (95%CI, 0.72- 0.93) and mean regression accuracy of 6.3 ± 1.0 s (95%CI, 4.3- 8.5 s) at 30 seed samples).
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 system of Giftakis to include performance metrics being defined by an area under a precision-recall curve (AU-PRC) for the classifier of at least 0.5. as taught by Constantino in order to provide metrics that better analyze a system’s ability to detect seizures with high accuracy using a large dataset of expert-validated ictal patterns from the iEEG recordings of RNS-implanted epilepsy patients (Constantino, Pg. 5 para. 4).
Claim(s) 6-7 and 9 is/are rejected under 35 U.S.C. 103 as being unpatentable over US 2020/0155829 to Giftakis et al. (herein Giftakis) in view of Expert-Level Intracranial Electroencephalogram Ictal Pattern Detection by a Deep Learning Neural Network to Constantino et al. (herein Constantino) as applied to claim 1 further in view of US 2014/0081348 to Fischell (herein Fischell) (cited by applicant).
In reference to at least claim 6
Giftakis modified by Constantino renders obvious a method according to claim 1. Giftakis further discloses wherein identifying values for the time parameter and the frequency parameter (e.g. para. 0070: A clinician may evaluate patient activity level monitored by one or both activity sensors 25, 36 and/or an external activity sensor, as well as the bioelectrical brain signals patient 12 during an evaluation period in order to determine the parameters for the seizure detection algorithm of IMD16...During the course of evaluating patient 12, the clinician may determine, for example, that the bioelectrical brain signal characteristics (e.g., amplitude, slope, pattern [time parameters], frequency, or frequency band characteristics [frequency parameters]) indicate an onset of a target seizure for which therapy delivery is desired).
Giftakis fails to explicitly disclose selecting a set of values for the time parameter and the frequency parameter that are associated with a frequency with which the first set of electrodes stimulates the region of the brain, wherein different sets of values for the time parameter and the frequency parameter are associated with different stimulation frequencies.
Fischell is in the field of stimulating tissue (abstract) and teaches selecting a set of values for the time parameter and the frequency parameter that are associated with a frequency with which the first set of electrodes stimulates the region of the brain (e.g. para. 0004: a break interval may separate two stimulation sequences. The one or more stimulation sequences, and any intervening break periods, may be repeated continuously, or on a pre-scheduled basis; para. 0012: the neurostimulation may comprise at least a first non-responsive stimulation mode, in which a low-frequency stimulation signal'(e.g., a stimulation signal having a primary frequency of 15.0 hertz or less) is delivered to the brain...the neurostimulation may comprise a second non-responsive stimulation mode, in which ahigh-frequency stimulation signal (e.g., a signal having a primary frequency greater than 15 hertz) may be applied to the brain), wherein different sets of values for the time parameter and the frequency parameter are associated with different stimulation frequencies (e.g. para. 0004: a break interval may separate two stimulation sequences. The one or more stimulation sequences, and any intervening break periods, may be repeated continuously, or on a pre-scheduled basis; para. 0012: the neurostimulation may comprise at least a first non-responsive stimulation mode, in which a low-frequency stimulation signal (e.g., a stimulation signal having a primary frequency of 15.0 hertz or less) is delivered to the brain...the neurostimulation may comprise a second non-responsive stimulation mode, in which a high-frequency stimulation signal (e.g., a signal having a primary frequency greater than 15 hertz) may be applied to the brain).
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 method of Giftakis to include parameters as taught by Fischell for the purpose of providing more options for stimulating the brain of a patient (Fischell, paras. 0004, 0012).
In reference to at least claim 7
Giftakis modified by Constantino renders obvious a method according to claim 6. Giftakis fails to explicitly disclose the method of claim 6, wherein a first set of values for the time parameter and the frequency parameter are associated with a low-frequency stimulation and a second set of values for the time parameter and the frequency parameter are associated with a high-frequency stimulation.
Fischell teaches a first set of values for the time parameter and the frequency parameter are associated with a low-frequency stimulation (e.g. para. 0004: a break interval may separate two stimulation sequences. The one or more stimulation sequences, and any intervening break periods, may be repeated continuously, or on a pre-scheduled basis; para. 0012: the neurostimulation may comprise at least a first non-responsive stimulation mode, in which a low-frequency stimulation signal (e.g., a stimulation signal having a primary frequency of 15.0 hertz or less) is delivered to the brain) and a second set of values for the time parameter and the frequency parameter are associated with a high-frequency stimulation (e.g. para. 0004: a break interval may separate two stimulation sequences. The one or more stimulation sequences, and any intervening break periods, may be repeated continuously, or on a pre-scheduled basis; para. 0012: the neurostimulation may comprise a second non-responsive stimulation mode, in which ahigh-frequency stimulation signal (e.g., a signal having a primary frequency greater than 15 hertz) may be applied to the brain).
It would have been obvious to one of ordinary skill in the art before the priority date to modify the method of Giftakis lo include parameters as taught by Fischell for the purpose of providing more options for stimulating the brain of a patient (Fischell, paras. 0004, 0012).
In reference to at least claim 9
Giftakis modified by Constantino renders obvious a method according to claim 6. Giftakis further discloses wherein identifying values for the time parameter and the frequency parameter (e.g. para. 0070: A clinician may evaluate patient activity level monitored by one or both activity sensors 25, 36 and/or an external activity sensor, as well as the bioelectrical brain signals patient 12 during an evaluation period in order to determine the parameters for the seizure detection algorithm of IMD16...During the course of evaluating patient 12, the clinician may determine, for example, that the bioelectrical brain signal characteristics (e.g., amplitude, slope, pattern [time parameters], frequency, or frequency band characteristics [frequency parameters]) indicate an onset of a target seizure for which therapy delivery is desired). It was well known in the art before the effective filing date of the claimed invention to adjust frequencies that are delivered to electrodes and sense data at the different frequencies to compare the effects different stimulation parameters have on a patient. Therefore it would have been well within the level of ordinary skill in the art to adjust the frequency with which the first set of electrodes stimulates the region of the brain from a first frequency to a second frequency; and in response to the adjusting, applying a second set of values for the time parameter and the frequency parameter to segment the electrical signal and determine powers of time- segmented portions of the electrical signal in place of a first set of values for the time parameter and the frequency parameter, wherein the second set of values is associated with the second frequency and the first set of values is associated with the first frequency in order to compare the effects on the patient based on the different stimulation parameters.
Claim(s) 16 is/are rejected under 35 U.S.C. 103 as being unpatentable over US 2020/0155829 to Giftakis et al. (herein Giftakis) in view of Expert-Level Intracranial Electroencephalogram Ictal Pattern Detection by a Deep Learning Neural Network to Constantino et al. (herein Constantino) as applied to claim 1 further in view of US 2009/0082691 to Denison et al. (herein Denison) (cited by applicant).
In reference to at least claim 16
Giftakis modified by Constantino renders obvious a method according to claim 1. Giftakis further discloses wherein the value for the frequency parameter comprises a bandwidth component (e.g. para. 0041: One type of seizure detection algorithm Indicates a seizure upon sensing of a bioelectrical brain signal that exhibits a certain characteristic, which may be...a frequency domain characteristic (e.g., an energy level in one or more frequency bands)). Giftakis fails to explicitly disclose a center-frequency component.
Denison is in the field of monitoring physiological signals (abstract) and teaches a center-frequency component (e.g. paras. 0108-0109: As an example, when monitoring akinesia, the selected frequency band may be the alpha frequency band (5 Hz to 15 Hz)...the signal in the ' selected frequency band may be produced by selecting the offset ( ) 87 such that the carrier frequency plus or minus the offset frequency (f±6) is equal to a frequency within the selected frequency band, such as the center frequency of the selected frequency band. In each case, as explained above, the offset may be selected to correspond to the desired band).
II would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method of Giftakis to include signal monitoring methods which include a center-frequency component as taught by Denison in order to provide frequency selective monitoring of physiological signals for allowing a user to select different frequency bands and change frequency bands manually or automatically(Denison, para. 0011).
Claim(s) 17 is/are rejected under 35 U.S.C. 103 as being unpatentable over US 2020/0155829 to Giftakis et al. (herein Giftakis) in view of Expert-Level Intracranial Electroencephalogram Ictal Pattern Detection by a Deep Learning Neural Network to Constantino et al. (herein Constantino) as applied to claim 1 further in view of US 2008/0033499 to Boileau et al. (herein "Boileau") (cited by applicant).
In reference to at least claim 17
Giftakis modified by Constantino renders obvious a method according to claim 1. Giftakis fails to explicitly disclose wherein the value for the frequency parameter comprises an upper cutoff frequency component and a lower cutoff frequency component.
Boileau is in the field of implantable cardiac systems (abstract) and teaches the value for the frequency parameter comprises an upper cutoff frequency component and a lower cutoff frequency component (e.g. para. 0022: The system comprises at least one implantable electrode arrangement that senses cardiac electrical activity and provides an intracardiac electrogram signal, a first high-pass filter with a cutoff frequency at an upper frequency break point that filters the intracardiac electrogram signal, and an equalizer that filters the filtered intracardiac electrogram signal. The equalizer has a transfer function derived by multiplying a reciprocal of the transfer function of the first high pass filter by a transfer function of a second high pass filter with a cutoff frequency at a lower frequency breakpoint).
It would have been obvious to one of ordinary skill in the art before the priority date to modify the method of Giftakis to include activity sensing that includes an upper cutoff frequency component and a lower cutoff frequency component as taught by Boileau in order to facilitate measurement of slowly changing features of a body part (Boileau, paras.0022-0026).
Claim(s) 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over US 2020/0155829 to Giftakis et al. (herein Giftakis) in view of Expert-Level Intracranial Electroencephalogram Ictal Pattern Detection by a Deep Learning Neural Network to Constantino et al. (herein Constantino) as applied to claim 1 further in view of US 2020/0100678 to Meyer et al. (herein Meyer) (cited by applicant).
In reference to at least claim 20
Giftakis modified by Constantino renders obvious a method according to claim 1. Giftakis further discloses in response to detecting a seizure event based on identification of one or more seizure positive time-segmented portions of the electrical signal (e.g. para. 0161: Processor 40 determines that for time period 96, brain signal 90 exhibited an average amplitude that Is greater than threshold TH. Accordingly, processor 40 determines that during time period 96 [time segment], the target seizure detected based on patient activity signal 92 is a true seizure. On the other hand, processor 40 determines that for time period 98 [time segment], brain signal 90exhibited normal behavior because an average amplitude of brain signal 90 during time period 98 was less than threshold TH), initiating stimulation of a region of the brain (e.g. para. 0060:it may be desirable to deliver electrical stimulation to brain 28 of patient 12upon detection of a sensory seizure; paras. 0072-0073:a signal generator within IMD16may generate the electrical stimulation therapy for DBS according to a therapy program that is selected at that given time in therapy...ln the example shown in FIG. 1, IMD 16 includes a memory to store a plurality of therapy programs that each defines a set of therapy parameter values (adjusted parameters]. In some examples, IMD 16 may select a therapy program from the memory based on various parameters, such as based on one or more characteristics of a bioelectrical brain signal).
Giftakis fails to explicitly disclose initiating stimulation of a second region of the brain different from the region of the brain stimulated by the first set of electrodes.
Meyer is in the field of brain stimulation (abstract) and teaches initiating stimulation of a second region of the brain different from the region of the brain stimulated by the first set of electrodes (e.g. para. 0064: FIG. 3 shows the exposed portion of brain tissue, which is marked by the boundary line 12. Within the boundary line 12, stimulation locations A1 to AS are marked on the monitor, the numbering indicating the sequence in which individual stimulations are to be performed. The circles joined to one another by a line at the respective stimulation locations in this case indicate the placements of the poles 5A and 5B of the stimulation electrode 5 [electrode sets; different areas of stimulation]).
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 method of Giftakis to include stimulation methods that include initiating stimulation of a second region of the brain different from the region of the brain stimulated by the first set of electrodes as taught Meyer in order to optimize the number of stimulations of the associated stimulation locations and the sequence of the stimulations (Meyer, paras. 0040-0046).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. US 2026/0013779 to Sheikh et al. which discloses a predictor of seizure outcome using per0-ictal scalp EEG data.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JENNIFER L GHAND whose telephone number is (571)270-5844. The examiner can normally be reached Mon-Fri 7:30AM - 3:30PM ET.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, JENNIFER MCDONALD can be reached at (571)270-3061. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/JENNIFER L GHAND/Examiner, Art Unit 3796
Prosecution Insights