DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claim 1-8 and 10-17 are rejected under 35 U.S.C. 101 because the claimed inventions are directed towards an abstract idea without significantly more.
Step 1- Is the claim to a statutory category of invention?
Claims 1-8 recite a method. Claims 10-18 recite a machine (i.e., a device). Therefore, the claims are to a statutory category of invention.
Step 2A, prong 1- Does the claim recite a judicial exception?
Claim 1 recites “extracting one or more features from the recorded electrical signals.” The recitation is an abstract idea mental process. The claim is directed towards an abstract idea mental process in that the action of extracting data from a signal can be performed in one of ordinary skills head. In the case of the instant application, one of ordinary skill in the art, such as a physician, could observe the recorded signal and extract (i.e., write down on a piece of paper) the features from the signal (such as the amplitude, wavelength, and time of peak occurrences).
Claim 1 recites “detecting clustering of the one or more extracted features of the recorded electrical signals.” The recitation is an abstract idea mental process. In the case of the instant application, the claim is directed towards an abstract idea mental process in that it recites detecting clustering. One of ordinary skill in the art could observe a signal, extract the features from the signal, and plot the features (MPEP 2106.04(a)(III): “The courts do not distinguish between mental processes that are performed entirely in the human mind and mental processes that require a human to use a physical aid (e.g., pen and paper or a slide rule) to perform the claim limitation.”). One of ordinary skill could then observe where datapoints of extracted features are clustered to determine groupings for the signal data. The limitation, although possibly tedious, could be performed in one’s head, with or without a pen and paper as an aid.
Claim 1 recites “identifying, by the neurostimulation device, an evoked response signal of interest from among the recorded electrical signals using the detected clustering of the one or more extracted features of the recorded electrical signals.” The recitation is an abstract idea mental process. Identifying an evoked response signals of interest among recordings of electrical signals is a mental process in that a physician or other skilled professional could look at extracted values from a recorded electrical signals to identify which signals are evoked response signals of interest. Further, the clustering of the signal datapoints could be used to identify evoked responses based on the groupings of the extracted features to determine which datapoints are from evoked responses. This is an abstract mental process in that one of ordinary skill in the art could observe the clustering of extracted features to determine signals of interest.
Regarding claim 10, the claim recites similar abstract idea mental processes as recited in claim 1 above. That is, extracting features of a recorded electrical signal, and detecting a clustering. Additionally, claim 10 recites “classify a recorded electrical signal as an evoked response signal of interest according to the detected clustering of the one or more extracted features of the recorded electrical signals.” This is an abstract idea mental process in that one of ordinary skill could observe the signals, and then classify the signals as an evoked response signal. One of ordinary skill could make an observation about the features of a signal and classify it mentally.
Step 2A, prong 2- Does the claim recite additional elements that integrate the judicial exception into a practical application?
Claim 1 does not include any additional elements that amount to integration of the abstract idea into a practical application. Claim 1 recites the additional elements of delivering neurostimulation to a stimulation lead and recording electrical signals. Delivering stimulation to a patient and recording the signals from the patient is recited at such a high level of generality that it amounts to insignificant, extra-solution activity of data gathering. Further, the preamble recites that the method is a computer implemented method for operating a stimulation lead. The recitation only further limits the field of use and does not integrate the judicial exception into a practical application.
Regarding claim 10, the limitations do not amount to integration of the abstract idea into a practical application. The claim recites the following limitations: “a stimulation circuit configured to deliver electrical neurostimulation to a subject when coupled to an implantable stimulation lead; a sensing circuit configured to sense electrical signals when coupled to the stimulation lead; a control circuit operatively coupled to the stimulation circuit and the sensing circuit, and configured to initiate delivery of neurostimulation to the subject and record sensed electrical signals resulting from the neurostimulation; and signal processing circuitry.” Sensing signals, delivering stimulation, and recording stimulation are recited at such a high level of generality that it amounts to nothing more than extra-solution activity data gathering. Further, the recited claim limitations describe generic computer structures (stimulation circuit, sensing circuit, control circuit, and signal processing circuitry) that are defined by the abstract mental processes performed. Therefore, the limitations do not integrate the invention into a practical application. Lastly, the preamble merely defines the field of use of the device as a neurostimulation device and does not integrate the abstract idea into a practical application.
Step 2B- Do the additional elements add significantly more to the judicial exception?
Claim 1 does not include any additional elements that amount to significantly more than an abstract idea. Claim 1 recites the additional elements of delivering neurostimulation to a stimulation lead and recording electrical signals. Delivering stimulation to a patient and recording the signals from the patient is recited at such a high level of generality that it amounts to insignificant, extra-solution activity of data gathering. Further, the preamble recites that the method is a computer implemented method for operating a stimulation lead. The recitation only further limits the field of use and does not amount to significantly more.
Claim 10 does not include any additional elements that amount to significantly more than an abstract idea. The claim recites the following limitations: “a stimulation circuit configured to deliver electrical neurostimulation to a subject when coupled to an implantable stimulation lead; a sensing circuit configured to sense electrical signals when coupled to the stimulation lead; a control circuit operatively coupled to the stimulation circuit and the sensing circuit, and configured to initiate delivery of neurostimulation to the subject and record sensed electrical signals resulting from the neurostimulation; and signal processing circuitry.” Sensing signals, delivering stimulation, and recording stimulation are recited at such a high level of generality that it amounts to nothing more than extra-solution activity data gathering. Further, the recited claim limitations describe generic computer structures (stimulation circuit, sensing circuit, control circuit, and signal processing circuitry) that are defined by the abstract mental processes performed. Therefore, the limitations do not amount to significantly more. Lastly, the preamble merely defines the field of use of the device as a neurostimulation device and not amount to significantly more.
Dependent Claims
Claim 2 further limits a mental process abstract idea (extracting and detecting).
Claim 3 further limits a mental process abstract idea (detecting and classifying) and recites an abstract idea mathematical concept (using kernel density estimation).
Claim 4 further limits a mathematical concept abstract idea (determining a value of a kernel function and KDE for all kernel function values). It also recites mental concept abstract ideas (identifying a higher density set of recorded signals and classifying recording electrical signals).
Claims 5 and 6 further limit a mathematical concept (calculating a normalized log, determining the KDE for kernel function values) and mental process abstract idea (identifying the higher density set of recorded electrical signals).
Claims 7 and 8 further limit a mental process (detecting the clustering) and mathematical concept abstract idea (computing the distance between recorded electrical signals).
Claim 11 further limits an abstract idea mental process.
Claim 12 further limits abstract idea mental processes and mathematical calculations.
Claim 13 further limits abstract idea mathematical calculations
Claim 14 further limits abstract idea mental processes and mathematical calculations.
Claim 15 further limits an abstract idea mental process.
Claim 16 further limits abstract idea mathematical concepts,
Claim 17 further limits abstract idea mental processes.
The limitations of dependent claims 2-8 and 11-17 listed above do not integrate the judicial exception into a practical application and do not amount to significantly more than the judicial exception.
In summary, claims 1-8 and 10-17 are directed to a judicial exception and are, therefore, patent-ineligible under 35 USC 101.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 15-18 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.
Regarding claim 15, the claim recites “the signal processing circuitry.” However, claim 9 does not recite a signal processing circuitry. Therefore, “the signal processing circuitry” lacks antecedent basis. It is possible the claim is supposed to be in reference to claim 10. For examination purposes, the claim will be interpreted as being the “signal processing circuitry” in reference to the device from claim 10.
Regarding claim 16, , the claim recites “the signal processing circuitry.” However, claim 9 does not recite a signal processing circuitry. Therefore, “the signal processing circuitry” lacks antecedent basis. It is possible the claim is supposed to be in reference to claim 10. For examination purposes, the claim will be interpreted as being the “signal processing circuitry” in reference to the device from claim 10.
Regarding claim 17, the claim recites “the signal processing circuitry.” However, claim 9 does not recite a signal processing circuitry. Therefore, “the signal processing circuitry” lacks antecedent basis. It is possible the claim is supposed to be in reference to claim 10. For examination purposes, the claim will be interpreted as being the “signal processing circuitry” in reference to the device from claim 10.
Claim 18 is rejected due to its dependency on claim 17. Additionally, claim 18 is indefinite for lack of antecedence in claim 17.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claim(s) 1, 2, 7, 9, 10, 15, and 17 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Crowder et al. (US 10130813 B2, “Crowder”).
Regarding claim 1, Crowder teaches a computer-implemented method of operating a neurostimulation device (Fig. 1B neurostimulator 110) when connected to an implantable stimulation lead (Fig. 1B; leads 124, 126), the method comprising: delivering neurostimulation to a subject using the neurostimulation device (para. (27); “an implantable neurostimulator configured to apply an electrical stimulation therapy to the neural tissue of a patient.”); recording electrical signals sensed using the implantable stimulation lead (Fig. 1B; para. (76); “an implantable neurostimulator system can be configured to receive with an implanted neurostimulator 110 electrographic signals (or ECoGs) sensed from a patient on one or more sensing channels.”); extracting one or more features from the recorded electrical signals (para. (77); “The neurostimulator includes “modules” and “subsystems” that enable the neurostimulator to process the sensed electrographic activity and analyze it on each sensing channel to extract features that likely are relevant to determining whether the electrographic activity evidences a neurological event, such as a seizure onset.”); detecting clustering of the one or more extracted features of the recorded electrical signals (para. (158); “A few to several features such as amplitude of the signal in the ECoG record, frequency of the signal in the ECoG record, may be extracted from the ECoG records and supervised machine learning and/or clustering techniques may be used on the extracted features for grouping ECoG records having similar types of neurological events.”); and identifying, by the neurostimulation device, an evoked response signal of interest from among the recorded electrical signals (para. (214); “The recorded data may include multiple measures of physiological activity, including for example, electrographic activity in the form of ECoG files, duration of detected events, rate of occurrences of detected events over time, as well as the amplitude of evoked potentials.”) using the detected clustering of the one or more extracted features (para. (70); “where ECoG records are clustered into groups based on similarity between the extracted features.”) of the recorded electrical signals (para. (214); “As noted above, other metrics of effectiveness may include… evoked potential “EP” amplitude…”).
Regarding claim 2, Crowder discloses the method of claim 1 (see above), wherein the extracting the one or more features of the recorded electrical signals includes measuring a magnitude of the recorded electrical signals (Table 2; “maximum” is shown as an extracted feature; Fig. 8A-F shows that the magnitude (in millivolts) is being recorded from the signal.) and a time of a greatest magnitude value of the recorded electrical signals (Fig. 8A-F; Shows current magnitude (measured in millivolts) recorded over time recordings); wherein detecting clustering includes detecting a cluster of recorded electrical signals in a feature space(para. (208); “a stimulation parameter subspace 1312 by running a clustering process on the collections 1302, 1304, 1306 of the stimulation parameter sets.”) including the greatest magnitude values and the times of the greatest magnitude values of the recorded electrical signals (Fig. 8A-F; Figure shows the current magnitude (measured in millivolts) plotted against time); and selecting the evoked response signal of interest from the detected cluster (para. (174); “For example, the identification of which electrode(s) are used to deliver the instance of stimulation therapy may comprise a stimulation parameter. Similarly, the polarity assigned to an electrode through which the instance of stimulation is delivered may be another parameter in the stimulation parameter space/subspace.).
Regarding claim 7, Crowder discloses the method of claim 1 (see above), wherein the detecting the clustering includes determining correlation of the one or more extracted features among the recorded electrical signals. (para. 250; " If a particular neurological event type or types can be detected in or other feature of interest can be extracted from the monitored electrographic signals and then correlated to whether a given stimulation parameter subspace is effective in achieving a desired therapeutic result, then the neurostimulator 110 further can be configured to monitor a variable that reflects the correlation.")
Regarding claim 9, Crowder discloses the method of claim 1 (see above), including the neurostimulation device adjusting the neurostimulation to the subject using the one or more extracted features of the identified evoked response signal of interest (para. (244); “the integration module allows the neurostimulation system to consider factors in addition to or other than the result of a mapping function before determining whether to adjust a stimulation for a patient when a particular neurological event, in these examples, a seizure onset neurological event type, is detected by the neurostimulator.”; As mentioned, the adjustments are made based the mapping. This mapping function derives from the extracted features in a subspace from the signals (see para. 246).
Regarding claim 10, Crowder discloses a neurostimulation device (Fig. 1B neurostimulator 110), the device comprising: a stimulation circuit configured to deliver electrical neurostimulation to a subject (para. (27); “an implantable neurostimulator configured to apply an electrical stimulation therapy to the neural tissue of a patient.”) when coupled to an implantable stimulation lead (Fig. 1B; para. (76); “an implantable neurostimulator system can be configured to receive with an implanted neurostimulator 110 electrographic signals (or ECoGs) sensed from a patient on one or more sensing channels.”); a sensing circuit configured to sense electrical signals when coupled to the stimulation lead (sensing subsystem 512; para. 90; “leads are coupled to the neurostimulator.” (which comprises of the sensing subsystem 512); a control circuit (Fig. 5; 510; “control interface”) operatively coupled to the stimulation circuit (Fig. 514; “sensory stimulator”) and the sensing circuit (Fig. 5B; sensing subsystem 512), and configured to initiate delivery of neurostimulation to the subject and record sensed electrical signals resulting from the neurostimulation (para. (81); “The neurostimulator further comprises modules and/or subsystems that can be configured to generate and deliver stimulation therapy in response to detection by the neurostimulator of a neurological event.”); and signal processing circuitry configured to: extract one or more features from the recorded electrical signals (para. (77); “The neurostimulator includes “modules” and “subsystems” that enable the neurostimulator to process the sensed electrographic activity and analyze it on each sensing channel to extract features that likely are relevant to determining whether the electrographic activity evidences a neurological event, such as a seizure onset.); detect clustering of the one or more extracted features of the recorded electrical signals (para. (158); “A few to several features such as amplitude of the signal in the ECoG record, frequency of the signal in the ECoG record, may be extracted from the ECoG records and supervised machine learning and/or clustering techniques may be used on the extracted features for grouping ECoG records having similar types of neurological events”); and classify a recorded electrical signal as an evoked response signal of interest according to the detected clustering of the one or more extracted features of the recorded electrical signals (para. (214); “As noted above, other metrics of effectiveness may include… evoked potential “EP” amplitude…”; In referring to the feature of the signal as an evoked potential and measuring its amplitude, Crowder is classifying the signal based on the evoked potential).
Regarding claim 15, Crowder discloses the device of claim 9 (see above), wherein the signal processing circuitry (para. (276); “The configuration module 1906, event detection module 1908, feature extraction module 1910, a probability/rank module 1912, subspace determination module 1914, integration module 1922, and optimization module 1924, may be software modules running in the processor 1918, resident/stored in the computer readable medium/memory 1920, one or more hardware modules coupled to the processor 1918, or some combination thereof.”; Fig. 19 represents a block diagram of the methods of Fig. 15, 17, and 19, which are all incorporated into the stimulation device.) is configured to detect the clustering of the one or more extracted features of the recorded electrical signals using correlation of the one or more extracted features among the recorded electrical signals. (para. (250); " If a particular neurological event type or types can be detected in or other feature of interest can be extracted from the monitored electrographic signals and then correlated to whether a given stimulation parameter subspace is effective in achieving a desired therapeutic result, then the neurostimulator 110 further can be configured to monitor a variable that reflects the correlation.").
Regarding claim 17, Crowder discloses the device of claim 9 (see above), wherein the signal processing circuitry (para. (160); “The method may be performed by one or more processors configured to execute the steps in the methods.”) is configured to: measure a magnitude of the recorded electrical signals (Table 2; “maximum” is shown as an extracted feature; Fig. 8A-F shows that the magnitude (in millivolts) is being recorded from the signal.) and a time of a greatest magnitude value of the recorded electrical signals (Fig. 8A-F; Shows current magnitude (measured in millivolts) recorded over time recordings); determine a cluster of recorded electrical signals in a feature space (para. (208); “a stimulation parameter subspace 1312 by running a clustering process on the collections 1302, 1304, 1306 of the stimulation parameter sets.”) including the greatest magnitude values and the times of the greatest magnitude values of the recorded electrical signals (Fig. 8A-F; Figure shows the current magnitude (measured in millivolts) plotted against time); and identify the evoked response signal of interest from the recorded electrical signals included in the determined cluster (para. (174); “For example, the identification of which electrode(s) are used to deliver the instance of stimulation therapy may comprise a stimulation parameter. Similarly, the polarity assigned to an electrode through which the instance of stimulation is delivered may be another parameter in the stimulation parameter space/subspace.”; This demonstrates that a signal corresponding to the identified electrode for an evoked response signal is determined from the subspace of the cluster).
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) 8 and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Crowder (US 10130813 B2, “Crowder”) in view of Zhu et al. (US 20120016445 A1, “Zhu”).
Regarding claim 8, Crowder discloses the method of claim 1 (see 102 rejection above). However, Crowder does not disclose wherein the detecting the clustering includes computing a distance between the recorded electrical signals in a feature space derived for the recorded electrical signals.
Zhu, in the same field of endeavor of neurostimulation devices and methods, discloses a technique for clustering electrical signals features. Zhu discloses wherein the detecting the clustering includes computing a distance between the recorded electrical signals in a feature space derived for the recorded electrical signals. (para. [0090]; “the first electrode clustering technique, an agglomerative algorithm is used in a hierarchical clustering analysis. This technique involves determining, as the pair of immediately neighboring electrode subsets determined in step 202, a pair of electrode subsets closest in proximity to each other than any other pair of electrode subsets is in proximity to each other, which is reiterated via step 208, and identifying the clustering relationship of the electrodes in step 210 by arranging the electrodes in hierarchical clustering structures.”)
It would have been obvious for one of ordinary skill in the art before the effective filing date to combine the methods of claim 1, as disclosed by Crowder, with the distance computation of electrode signal subsets as disclosed by Zhu. Implementing the method of computing the distance between signal subsets to compare clusters of electrode signals, as disclosed by Zhu, with the method of claim 1 would have been an obvious improvement of Crowder’s clustering technique since comparisons could be made between the signals to correctly identify groupings and the similarities between those groupings. Therefore, claim 8 is obvious over Crowder, et al. and Zhu, et al.
Regarding claim 16, Crowder discloses the device of claim 9 (see above), wherein the signal processing circuitry (para. (276); “subspace determination module 1914…, may be software modules running in the processor 1918, resident/stored in the computer readable medium/memory 1920, one or more hardware modules coupled to the processor 1918, or some combination thereof.”; Fig. 19 represents a block diagram of the methods of Fig. 15, 17, and 19, which are all incorporated into the stimulation device.) is configured to: derive a feature space for the one or more extracted features of the recorded electrical signals (para. (269); “a subspace determination module 1914, configured to determine a stimulation parameter subspace and default stimulation parameter set for the neurological event type detected by the neurostimulator.”; Fig. 19 shows the feature extraction module (1910) in conjunction with the subspace determination module (1914) via arrows feeding into the processing system (1926) for processing obtained signals.); However, Crowder does not disclose where the processor is configured to compute a distance between the recorded electrical signals in the derived feature space.
Zhu discloses where the system is configured to compute [a] distance between the recorded electrical signals in the derived feature space. (para. [0090]; “the first electrode clustering technique, an agglomerative algorithm is used in a hierarchical clustering analysis. This technique involves determining, as the pair of immediately neighboring electrode subsets determined in step 202, a pair of electrode subsets closest in proximity to each other than any other pair of electrode subsets is in proximity to each other, which is reiterated via step 208, and identifying the clustering relationship of the electrodes in step 210 by arranging the electrodes in hierarchical clustering structures.”).
It would have been obvious for one of ordinary skill in the art before the effective filing date to combine the device of claim 9, as disclosed by Crowder, with the processor configured to compute the distance of electrode signal subsets as disclosed by Zhu. Implementing circuitry for computing the distance between signal subsets to compare clusters of electrode signals, as disclosed by Zhu, with the device of claim 10 would have been an obvious improvement of Crowder’s device since implementing a processor configured to perform this clustering technique would allow the device to compare similarities (i.e., how close or distant the subspaces are from each other) that would correctly identify the groupings. . Therefore, claim 16 is obvious over Crowder, et al. and Zhu, et al.
Claims 3, 11, and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Crowder (US 10130813 B2, “Crowder”) in view of Bhattacharya et al. (US 20120016445 A1, “Bhattacharya”).
Regarding claim 3, Crowder discloses the method of claim 1 (see 102 rejection above). Further, Crowder discloses obtaining evoked potentials from ECoG measurements (para. (214); “As noted above, other metrics of effectiveness may include… evoked potential “EP” amplitude…”). However, Crowder does not disclose wherein the detecting the clustering includes classifying the recorded electrical signals as either evoked response signals or artifact signals using kernel density estimation (KDE) of the one or more extracted features of the recorded electrical signals.
Bhattacharya, in the same field of endeavor of classifying signals, discloses methods for classifying Photoplethysmography (PPG) signals for coronary artery disease (CAD). Bhattacharya discloses wherein the detecting the clustering includes classifying the recorded electrical signals as either evoked response signals or artifact signals using kernel density estimation (KDE) of the one or more extracted features of the recorded electrical signals (abstract; “Kernel density estimate (KDE) is used to vary the feature distribution and create multiple data template from a single parent signal. PPG signal is again reconstructed from the distribution pattern using non-parametric techniques. The generated synthetic data set is used to build the two stage cascaded classifier to classify CAD and Non CAD, wherein the classifier design enables reducing bias towards any class”.)
It would have been obvious to one of ordinary skill in the art before the effective filing date to include the kernel density estimation of Bhattacharya with the methods of claim 1 as disclosed by Crowder. Kernel density is a known technique that is demonstrated as an effective way to classify signals, as demonstrated by Bhattacharya. Further, it would have been obvious to classify the signals as evoked potentials or artefact signals since Bhattacharya demonstrates the technique of classifying signals as CAD and non-CAD. Crowder is measuring evoked potentials, and Bhattacharya proves that KDE can be used to classify signal data into a clustering of binary categories, such as CAD and non-CAD. It would be obvious to use the same technique and classify the signals as either evoked potentials or artefacts. Lastly, although Bhattacharya only performs this method with a single PPG signal, it would have been obvious to repeat the KDE technique for multiple signals. This would be an obvious repetition of steps to repeat the technique for multiple signals.
Regarding claim 11, Crowder discloses the device of claim 10 (see 102 rejection above). However, Crowder does not disclose wherein the signal processing circuitry is configured to identify a group of the recorded electrical signals as evoked response signals using kernel density estimation (KDE) of the one or more extracted features of the recorded electrical signals.
Bhattacharya discloses wherein the signal processing circuitry is configured to identify a group of the recorded electrical signals as evoked response signals using kernel density estimation (KDE) of the one or more extracted features of the recorded electrical signals. (Abstract; ““Kernel density estimate (KDE) is used to vary the feature distribution and create multiple data template from a single parent signal. PPG signal is again reconstructed from the distribution pattern using non-parametric techniques. The generated synthetic data set is used to build the two stage cascaded classifier to classify CAD and Non CAD, wherein the classifier design enables reducing bias towards any class”; para. [0076]; “At step 208 of the method 200, the one or more hardware processors 104 are configured to fit a gaussian kernel density estimate (KDE) to each of the plurality of sets of observational values.”)
It would have been obvious to one of ordinary skill in the art before the effective filing date to combine the device of claim 10, as disclosed by Crowder, with the processor capable of performing kernel density estimation as disclosed by Bhattacharya. As mentioned (see claim 3 rejection), it would have been obvious to combine the technique of kernel density estimation to classify bioelectrical signals with the methods of claim 1. Further, it would have been obvious to include a processor that could perform the KDE technique in the neurostimulation device. A processor is shown, by Bhattacharya, as being capable of clustering signals into classification categories. Crowder is classifying similar bioelectrical signals, and doing so with a processor configured to perform KDE to cluster the signals into categories would be advantageous in performing this function.
Regarding claim 19, Crowder discloses a non-transitory computer readable storage medium (Fig. 18; computer-readable medium/memory 1920) including instructions that when performed by processing circuitry of a neurostimulation system (para. (270); “The software, when executed by the processor 1916, causes the modules to perform the various functions described herein for any particular module.”), cause the neurostimulation system to perform actions including: delivering neurostimulation energy to at least one implantable neurostimulation lead of the neurostimulation system (para. (27); “an implantable neurostimulator configured to apply an electrical stimulation therapy to the neural tissue of a patient.”; Fig. 1B shows the electrodes, where stimulation is provided, on lead 20A and 20B); recording electrical signals sensed using the implantable stimulation lead (Fig. 1B; para. (76); “an implantable neurostimulator system can be configured to receive with an implanted neurostimulator 110 electrographic signals (or ECoGs) sensed from a patient on one or more sensing channels.”); extracting one or more features from the recorded electrical signals (signals (para. (77); “The neurostimulator includes “modules” and “subsystems” that enable the neurostimulator to process the sensed electrographic activity and analyze it on each sensing channel to extract features that likely are relevant to determining whether the electrographic activity evidences a neurological event, such as a seizure onset.”); detecting clustering of the one or more extracted features of the recorded electrical signals (para. (158); “A few to several features such as amplitude of the signal in the ECoG record, frequency of the signal in the ECoG record, may be extracted from the ECoG records and supervised machine learning and/or clustering techniques may be used on the extracted features for grouping ECoG records having similar types of neurological events.”); and adjusting the neurostimulation based on the one or more extracted features of at least one identified evoked response signal. (para. (244); “the integration module allows the neurostimulation system to consider factors in addition to or other than the result of a mapping function before determining whether to adjust a stimulation for a patient when a particular neurological event, in these examples, a seizure onset neurological event type, is detected by the neurostimulator.”; As mentioned, the adjustments are made based the mapping function. This mapping function derives from the extracted features in a subspace from the signals (see Crowder para. 246). However, Crowder does not disclose classifying the recorded electrical signals as either an evoked response activity signal or a signal artifact using the clustering of the one or more extracted features of the recorded electrical signals.
Bhattacharya discloses classifying the recorded electrical signals as either an evoked response activity signal or a signal artifact using the clustering of the one or more extracted features of the recorded electrical signals. (abstract; “Kernel density estimate (KDE) is used to vary the feature distribution and create multiple data template from a single parent signal. PPG signal is again reconstructed from the distribution pattern using non-parametric techniques. The generated synthetic data set is used to build the two stage cascaded classifier to classify CAD and Non CAD, wherein the classifier design enables reducing bias towards any class.”; The classifying of CAD or non-CAD is based on a form of clustering (KDE) which classifies signal data based on the signal density.)
It would have been obvious to one of ordinary skill in the art before the effective filing date to combine the non-transitory computer readable storage medium with instructions to perform the actions of claim 19, as disclosed by Crowder, with the classification methods of Bhattacharya. Bhattacharaya uses a binary system (classifying the signals as CAD or non-CAD) to classify signals using a well-known clustering method (KDE). It would have been obvious to use this same clustering technique with evoked response signals in the same binary fashion (either evoked response or not evoked response). This would be an obvious improvement as the stimulation device would be able to filter out signal features that are not evoked potentials, reducing recordings of noise. Further, it would have been obvious to include instructions in a stimulation device, as disclosed by Crowder, since Crowder is also in the field of delivering stimulation to a patient via an implantable stimulation device.
Claims 18 is rejected under 35 U.S.C. 103 as being unpatentable over Crowder (US 10130813 B2, “Crowder”) in view of Hageman et al. (US 20230166111 A1, “Hageman”).
Regarding claim 18, Crowder discloses the device of claim 17 (see 102 rejection above), wherein the signal processing circuitry is configured to identify multiple evoked response signals of interest in the identified cluster of recorded electrical signals (para. (158); “A few to several features such as amplitude of the signal in the ECoG record, frequency of the signal in the ECoG record, may be extracted from the ECoG records and supervised machine learning and/or clustering techniques may be used on the extracted features for grouping ECoG records having similar types of neurological events.”; Grouping ECoG records implies that multiple ECoGs are identified as signals of interest.). However, Crowder does not disclose wherein the control circuit is configured to set a stimulation configuration of the neurostimulation to the stimulation configuration that produced the highest amplitude evoked response signal of the identified evoked response signals of interest.
Hageman, in the same field of endeavor of neural stimulation and adjusting stimulation parameters, discloses a neurostimulation device for measuring local field potentials and determining which electrodes receive stimulation. Hageman discloses that the neurostimulation device comprises a control circuit configured to produced the highest amplitude evoked response signal of the identified evoked response signals of interest. (para. [0086]; “As described above, the processing circuitry may control stimulation generation circuitry to deliver a plurality of electrical stimulation signals via the determined one or more electrodes, where the plurality of electrical stimulation signals each include at least one different therapy parameter.”; para. [0089]; “the processing circuitry may select the evoked potential signal of the respective evoked potential signals having the highest amplitude.”).
It would have been obvious for one of ordinary skill in the art before the effective filling date to incorporate Hageman’s control circuitry for selecting evoked potential signals having the highest amplitude into Crowder’s device as an additional circuitry component because doing so would allow the device to determine the most effective configuration. Additionally, incorporating circuitry with the method of clustering would provide circuitry for extracting the highest amplitude. Therefore, claim 18 is obvious over Crowder, et al. and Hageman, et al.
Allowable Subject Matter
Claim 4, 5, 6, 12, 13, 14, and 20 are free of the art. However, the claims are still rejected under USC 101 and 112.
Claims 4, 5, 6, 12, 13, 14, and 20 are novel since they use a kernel function on recorded signals, determine the KDE for the kernel values, identify higher and lower density regions of KDEs, and classify the signals based on a threshold. The subject matter is distinguishable from prior art in that prior art may disclose a kernel density estimation being used, but the instant application’s disclosure of using kernel functions and performing KDEs goes beyond just generic inclusion of the KDE by determining a value of a kernel function and performing the KDE on the values. The instant application also classifies the signals based on the KDE meeting a threshold and identifying higher and lower densities. The closest prior art, Crowder (US 10130813 B2), describes clustering methods for classifying signals, but does not mention kernel density estimation or kernel functions. Bhattacharya (US 20210342641 A1), another prior art reference that is concerned with classifying bioelectrical signals, uses KDE on PPG signals to classify CAD. However, the Bhattacharya does not identify a higher and lower signal density based on a threshold to classify the signals.
Claim 20 is objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to OWEN LEWIS MARSH whose telephone number is (571)272-8584. The examiner can normally be reached 7:30am – 5pm (M-Th) and 8am – noon (F).
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Jennifer McDonald can be reached at (571) 270-3061. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/OWEN LEWIS MARSH/Examiner, Art Unit 3796
/Jennifer Pitrak McDonald/Supervisory Patent Examiner, Art Unit 3796