CTNF 18/088,777 CTNF 101313 DETAILED ACTION Notice of Pre-AIA or AIA Status 07-03-aia AIA 15-10-aia The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA. Claim Status Claims 1-20 are pending. Priority This application claims benefit of application no. 63/403,294 filed 09/01/2022. The instant application has the effective filing date of 01 September 2022. Information Disclosure Statement The information disclosure statement (IDS) submitted on 02/07/2023 and 08/07/2023 are in compliance with the provisions of 37 CFR 1.97. NPL cite no. 1, listed on the IDS filed 08/07/2023, was not considered as an English translation was not provided. Accordingly, the information disclosure statements have been considered by the examiner. Drawings The drawings, submitted on 03/24/2023, are accepted by the examiner. 07-30-03-h AIA Claim Interpretation 07-30-03 AIA The following is a quotation of 35 U.S.C. 112(f): (f) Element in Claim for a Combination. – An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof. The following is a quotation of pre-AIA 35 U.S.C. 112, sixth paragraph: An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof. This application includes one or more claim limitations that do not use the word “means,” but are nonetheless being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, because the claim limitation(s) uses a generic placeholder that is coupled with functional language without reciting sufficient structure to perform the recited function and the generic placeholder is not preceded by a structural modifier. Such claim limitations is are: “deep brain stimulation module” in claims 1 and 11. “virtual brain network module” in claims 1 and 11. “feature extraction module” in claims 1 and 11. “reinforcement learning module” in claims 1 and 11. Because these claim limitations are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, they are being interpreted to cover the corresponding structure described in the specification as performing the claimed function, and equivalents thereof. The disclosure states all modules have access to a computer processor [fig. 1]. It further states the deep brain stimulation simulation module is adapted to combine a deep brain stimulation waveform according to a stimulation frequency and a stimulation amplitude, and output the deep brain stimulation waveform[0005]; the virtual brain network module is adapted to receive the deep brain stimulation waveform [0005], calculate the reward parameter, and output the synaptic signal [0033]; the feature extraction module is adapted to receive the synaptic signal and extract multiple feature values [0005]; and the reinforcement learning module is adapted to train the deep brain stimulation neural network based on the feature values and the reward parameter [0005]. Therefore, the reinforcement learning module appears to be an algorithm with a processor for performing computer implementing functions (MPEP 2181 II(B)). However, the remaining modules appear to describe structures capable of performing both algorithmic tasks and that of receiving and outputting signals and waveforms from a deep brain stimulator and sensor [fig. 3]; and it is unclear if structure can be met with one mere embodiment as an algorithmic. See Cardiac Pacemakers, Inc. v. St. Jude Med., Inc ., 296 F.3d 1106, 1115-18, 63 USPQ2d 1725, 1731-34 (Fed. Cir. 2002). As such, the specification in regards to the deep brain stimulation simulation module, virtual brain network module, and feature extraction module lack the corresponding structure required by 35 U.S.C. 112 . If applicant does not intend to have these limitations interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, applicant may: (1) amend the claim limitation(s) to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph (e.g., by reciting sufficient structure to perform the claimed function); or (2) present a sufficient showing that the claim limitation(s) recite(s) sufficient structure to perform the claimed function so as to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. Claim Rejections - 35 USC § 112 07-30-01 AIA The following is a quotation of the first paragraph of 35 U.S.C. 112(a): (a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention. The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112: The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention. 07-31-01 Claims 1-20 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA), first paragraph, as failing to comply with the written description requirement . The claims contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the invento(s, at the time the application was filed, had possession of the claimed invention, for the following reasons. Independent claims 1 and 11 recite a “deep brain stimulation simulation module”, “virtual brain network module”, and “feature extraction module,” which lack the corresponding structure required by 35 U.S.C. 112. As such, these limitations also lack sufficient structure required under 112 (a), written description. The dependent claims also fail to remedy the aforementioned problem and are rejected on similar grounds. 07-30-02 AIA 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. 07-34-01 Claims 1-20 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 for the following reasons. 07-34-23 Claim limitations “deep brain stimulation simulation module”, “virtual brain network module”, and “feature extraction module,” invokes 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. However, the written description fails to disclose the corresponding structure, material, or acts for performing the entire claimed function and to clearly link the structure, material, or acts to the function. The dependent claims also fail to remedy the aforementioned problem and are rejected on similar grounds. Therefore, the claims are indefinite and is rejected under 35 U.S.C. 112(b) or pre-AIA 35 U.S.C. 112, second paragraph. Applicant may: (a) Amend the claim so that the claim limitation will no longer be interpreted as a limitation under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph; (b) Amend the written description of the specification such that it expressly recites what structure, material, or acts perform the entire claimed function, without introducing any new matter (35 U.S.C. 132(a)); or (c) Amend the written description of the specification such that it clearly links the structure, material, or acts disclosed therein to the function recited in the claim, without introducing any new matter (35 U.S.C. 132(a)). If applicant is of the opinion that the written description of the specification already implicitly or inherently discloses the corresponding structure, material, or acts and clearly links them to the function so that one of ordinary skill in the art would recognize what structure, material, or acts perform the claimed function, applicant should clarify the record by either: (a) Amending the written description of the specification such that it expressly recites the corresponding structure, material, or acts for performing the claimed function and clearly links or associates the structure, material, or acts to the claimed function, without introducing any new matter (35 U.S.C. 132(a)); or (b) Stating on the record what the corresponding structure, material, or acts, which are implicitly or inherently set forth in the written description of the specification, perform the claimed function. For more information, see 37 CFR 1.75(d) and MPEP §§ 608.01(o) and 2181. Claim Rejections - 35 USC § 101 07-04-01 AIA 07-04 35 U.S.C. 101 reads as follows: Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title. Claims 1-20 are rejected under U.S.C 101 because the claimed invention is directed to abstract ideas without significantly more, as detailed in the analysis below. Eligibility Step 1: Subject matter eligibility evaluation in accordance with MPEP § 2106: Claims 1-10 are directed to a statutory category (system). Claim 11-20 are directed to a statutory category (method). Therefore, in accordance with MPEP § 2106.03 all claims have patent eligible subject matter. [Eligibility Step 1: YES] Eligibility Step 2A: This step determines whether a claim is directed to a judicial exception in accordance with MPEP § 2106. Eligibility Step 2A -- Prong One: Limitations are analyzed to determine if the claims recite any concepts that could equate to a judicial exception (i.e. abstract idea, law of nature, or natural phenomenon). Possible judicial exceptions are explored below. Recitations of Judicial Exceptions: Claims 1 and 11: virtual brain network module adapted to calculate a reward parameter; (mathematical concept) reinforcement learning module, adapted to train the deep brain stimulation neural network based on the plurality of feature values and the reward parameter (mathematical concept, mental process) Claims 2 and 12: a thalamic error index is calculated according to the virtual brain cortical signal and the virtual thalamic action potential signal. (mathematical concept) Claims 3 and 13: wherein the virtual brain network module is more adapted to calculate the reward parameter according to the thalamic error index. (mathematical concept) Claims 4 and 14: wherein the reward parameter is related to a revised score, a deep brain stimulation energy expenditure penalty, a current state penalty, and a compensation score (mathematical concept) Claims 5 and 15: wherein the reward parameter is a sum of each of the revised score, the deep brain stimulation energy expenditure penalty, the current state penalty, and the compensation score multiplied by respective weight parameters (mathematical concept) Step 2A – Prong One Analysis: Analysis techniques such as scoring using equations, calculations, sums, and weighting, recite mathematical calculations and relationships that fall under the mathematical concept grouping of abstract ideas. Analysis techniques such as training a neural network, as instantly recited, can be done using a combination of mathematical concepts and making mental determinations of data such as feature selection and/or data splitting, which equate to techniques which fall under the mental process grouping of abstract ideas. Therefore, the claims are found to recite judicial exceptions. [Eligibility Step 2A – Prong One: YES] Eligibility Step 2A – Prong Two: A claim that integrates a judicial exception into a practical application will apply, rely on, or use the judicial exception in a manner that imposes a meaningful limit on the judicial exception. If the claim contains no additional claim elements beyond the abstract idea, the claim fails to integrate the abstract idea into a practical application (MPEP 2106.04(d)). Additional elements are recited, categorized, and analyzed below. Data Gathering Elements: Claims 1 and 11: a virtual brain network module, adapted to receive the deep brain stimulation waveform, output a synaptic signal, and store the reward parameter to the memory; a feature extraction module, adapted to receive the synaptic signal, extract a plurality of feature values according to the synaptic signal, and store the plurality of feature values into the memory; Claims 6 and 16: wherein the plurality of feature values comprises Hjorth parameters, a β band power, and a sample entropy, wherein the Hjorth parameters comprises a Hjorth activity indicator, a Hjorth mobility indicator, and a Hjorth complexity indicator Computer/Neural Network Components: Claims 1 and 11: a memory, storing a deep brain stimulation neural network ; and a processor, coupled to the memory, the processor comprising Claims 7 and 17: wherein the reinforcement learning module is a twin-delayed deep deterministic policy gradient (TD3) architecture. Sensing Components: Claims 1 and 11: deep brain stimulation simulation module, adapted to combine a deep brain stimulation waveform according to a stimulation frequency and a stimulation amplitude and output the deep brain stimulation waveform; output the stimulation frequency and the stimulation amplitude Claims 2 and 12: wherein the virtual brain network module is more adapted to generate a virtual brain cortical signal and a virtual thalamic action potential signal Claims 8 and 18: wherein the deep brain stimulation waveform is a biphasic pulse wave Claims 9 and 19: a deep brain stimulator, connected to the deep brain stimulation simulation module and a subject brain, adapted to use the stimulation frequency and the stimulation amplitude output by the deep brain stimulation simulation module as the deep brain stimulation waveform to generate a deep brain stimulation current corresponding to the deep brain stimulation waveform, and stimulate the subject brain with the deep brain stimulation current; and a sensor, connected to the feature extraction module and the subject brain, adapted to sense the synaptic signal output from the subject brain; wherein the feature extraction module receives the synaptic signal output from the sensor and extracts the plurality of feature values according to the synaptic signal, the reinforcement learning module outputs the stimulation frequency and the stimulation amplitude to the deep brain stimulation module through a trained deep brain stimulation neural network Claims 10 and 20: wherein the sensor is more adapted to sense a brain cortical signal and a thalamic action potential signal of the subject brain Step 2A – Prong Two Analysis: The data gathering elements are found to recite insignificant extra-solution activities in the form of mere data gathering activities per MPEP 2106.05(g). The generic computer components (memory, processor) provide mere instructions to implement the abstract ideas onto a technological environment per Alice Corp., 573 U.S. at 223, 110 USPQ2d at 1983. See also 573 U.S. at 224, 110 USPQ2d at 1984. Though the components describing the neural network (claims 7 and 17) are not generic computer components, they are recited at a level of generality that they also merely act as a tool to apply the judicial exceptions. The sensing components receive signals to be manipulated by the judicial exceptions and merely output them. As such, they amount to necessary data gathering and outputting, classified as insignificant extra-solution activity per MPEP 2106.05(g). To overcome this rejection , consider amending the independent claims in a way which the output of the sensing components actively performs a particular treatment for Parkinson’s disease, via the requirements of MPEP 2016.04(d). As such, the additional elements, when viewed separately and in the context of a whole claimed invention, do not integrate the judicial exceptions into practical application. [Eligibility Step 2A – Prong Two: NO] Eligibility Step 2B: Claim elements are probed for inventive concept equating to significantly more than the judicial exception (MPEP 2106.04(II)). Step 2B Analysis: The data gathering elements are found to be well-understood, routine, and conventional per Merk et al. (Experimental Neurology; Vol. 351; May 2022) which reviews the parameters listed within the context of machine learning based brain signal decoding for intelligent deep brain stimulation. The generic computer components are further found to be well-understood, routine, and conventional per Versata Dev. Group, Inc. v. SAP Am., Inc., 793 F.3d 1306, 1334, 115 USPQ2d 1681, 1701 (Fed. Cir. 2015); OIP Techs., 788 F.3d at 1363, 115 USPQ2d at 1092-93 for storing and retrieving information in memory and Alice Corp., 573 U.S. at 225, 110 USPQ2d at 1984 (MPEP 2106.05 (a)). The neural network components are well-understood, routine, and conventional per Naya et al. (IEEE Access; Vol. 9; 2021) which explicitly states TD3 architecture is known as a state-of-the-art deep reinforcement learning algorithm (page 2, column 2). The sensing components and are found to be well-understood, routine, and conventional per Vissani et al. which reviews deep brain stimulation systems. As such, the additional elements are further found to lack inventive concept. [Eligibility Step 2B: NO] Therefore, claims 1-20 are directed to judicial exceptions without significantly more and are rejected under 35 U.S.C 101. Claim Rejections - 35 USC § 103 07-06 AIA 15-10-15 In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status. 07-20-aia AIA 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. 07-23-aia AIA The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows: 1. Determining the scope and contents of the prior art. 2. Ascertaining the differences between the prior art and the claims at issue. 3. Resolving the level of ordinary skill in the pertinent art. 4. Considering objective evidence present in the application indicating obviousness or nonobviousness. 07-20-02-aia AIA This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention. 07-21-aia AIA Claim s 1-4 and 11-14 are rejected under 35 U.S.C. 103 as being unpatentable over Lu et al. (IDS filed 02/07/2023; NPL; cite no. 13: 2020) . Lu et al. describes a method of applying reinforcement learning to Deep Brain Stimulation in a computational model of Parkinson’s Disease. Claims 1 and 11 are directed to systems and methods that combine a deep brain simulation module with a deep brain simulation waveform, based on a stimulation frequency and amplitude; and output the deep brain stimulation waveform. Lu et al. teaches modelling the deep brain stimulation (DBS) as IDBS= iD H(sin(2πt/ρD))×[1−H(sin(2π(t+δD)/ρD)], where iD denotes the stimulation amplitude (page 5, column 1); and the waveform of DBS will become a square-like pulse with a frequency approximating 120Hz (page 8, column 1) , delivered via an implanted pulse generator (page 1, column 1). Claims 1 and 11 are further directed to a virtual brain network module receiving the deep brain stimulation waveform intended to output a synaptic signal; and calculating and storing a reward parameter. Lu et al. teaches Iapp, the constant bias current can be viewed as the net synaptic input (page 2, column 2); spiking neuronal models of the basal ganglia (BG) network simulate DBS in the four primary cell types: the subthalamic nucleus (STN), internal globus pallidus (GPi) , globus pallidus externus (GPe), and TH neurons , in which all of them are connected by simulated synaptic couplings (page 9, column 1); the value function denotes the prediction of the future reward (page 6, column 1); and the controller (agent) takes an action at which will cause the states of the environment change and receive the reward (page 5, column 2). Claims 1 and 11 are further directed to a feature extraction module receiving the synaptic signal; extracting, and storing at least two feature values based on the signal. Lu et al. teaches modelling the Parkinsonian state by decreasing the constant bias currents Iapp applied to the STN, GPe, GPi and TH neurons parameters, detailed in table I (page 4, column 1), which lists approximately 28 variables for each synaptic variable and cell type (page 3, table I). Claims 1 and 11 are further directed to a reinforcement learning module training the deep brain stimulation neural network based on the feature values and reward parameters; and outputting the stimulation frequency and amplitude to the deep brain stimulation simulation module. Lu et al. teaches developing closed-loop control strategy based on a specific variable that reflects ongoing changes of the patient’s clinical states (page 1, column 2), in which the optimal control action can be achieved by maximizing the reward, then rewriting the value function with the optimal control action (page 6, column 2); and incorporating linear function approximators known as Cerebellar Model Articulation Controller neural network (CMAC) into the actor and critic; performing two sequential vector mappings; and calculating the output of the network as a scalar product of the association and weight vector (page 6, column 2). Lu et al. further teaches DBS is a neurosurgical technique, which high-frequency mono-polar pulse trains are delivered via an implanted pulse generator and injected into areas of basal ganglia network (BG) (page 1, column 1); a non-regular incoming signal from the SMC to thalamic neurons was modeled as a series of monophasic current pulses with amplitude of 3.5μ A/cm 2 and duration of 5ms (page 3, column 1); and according to the RL algorithm, the adjustable parameter at each time interval between two successive states SGi is the amplitude of external stimulation (page 8, column 1). Claims 2 and 12 are directed to using the virtual brain network module to generate a virtual brain cortical signal and a virtual thalamic action potential signal; and calculating a thalamic error index based on both virtual signals. Lu et al. teaches a reliability index (RI) is used to quantify the relay reliability of TH as RI = 1 – (Nerror/Nsmc), where each input pulse from sensorimotor cortex (SMC) results in a single action potential in each TH neuron (page 4, column 1); Nerror denotes the total number of errors in thalamic transmission; and Nsmc is the total number of SMC input (page 4, column 2). Claims 3 and 13 are directed to calculating the reward parameter with the virtual brain network module based on the thalamic error index. Lu et al. teaches the objective of closed-loop optimal control is to maximize relay reliability, in which the maximal relay reliability corresponds to minimal synaptic oscillation, and influences the reward calculation (page 7, column 2). Claims 4 and 14 are directed to the reward parameter being related to a revised score, deep brain stimulation energy expenditure penalty, current state penalty, and compensation score multiplied by respective weight parameters. Lu et al. teaches a good control algorithm seeks to maximize relay reliability as well as minimize the energy exerted in stimulation (page 5, column 1) because in addition to the faithfulness of thalamic relay, represented by the thalamic error index (RI), the energy expenditure of stimulation is also concerned, because if a closed-loop stimulation can restore the RI, but requires more energy, it is no need to use it to replace DBS (page 8, column 2). Lu et al. further teaches incorporating within the reward parameter γ(0<γ≤1), as a discount factor which determines the present value of future rewards; and if γ approaches 0, the agent is more concerned with the immediate reward, while if γ approaches 1, the agent takes future rewards into account more strongly; V~(St) denotes the estimate of the value function at state S, where γ is the discount factor and the agent can anticipate to take an action which will generate higher reward based on value function (page 6, column 1). Lu et al. does not explicitly teach singular structures adapted to perform the tasks of the deep brain stimulation simulation, virtual brain network, and feature extraction modules. However, the method as a whole teaches performing the steps required of them. As such, the use elements which perform the same function, for an identical purpose would also be obvious to one of ordinary skill in the art . 07-21-aia AIA Claim s 5 and 15 are rejected under 35 U.S.C. 103 as being unpatentable over Lu et al. (IDS filed 02/07/2023; NPL; cite no. 13: 2020), as applied to claims 1-4 and 11-14 above, and in further view of Naya et al. (IEEE Access; Vol. 9; 2021) Lu et al. teaches a method of using deep brain stimulation to treat Parkinson’s disease in which the reward parameter is calculated based on relay reliability, energy expenditure and discount factor penalties. Claims 5 and 15 are directed to the reward parameter being a sum of each revised score, deep brain stimulation energy expenditure penalty, current state penalty, and compensation score multiplied by respective weight parameters. Lu et al. further teaches calculating a cumulative reward from an initial state to end state, using equation 13: PNG media_image1.png 72 123 media_image1.png Greyscale (page 6, column 1). Lu et al. does not explicitly teach the mathematical operator used to incorporate energy expenditure into this calculation. Naya et al. describes the use of spiking neural networks for energy-efficient hexapod motion in deep reinforcement learning. Naya et al. teaches in Deep Reinforcement Learning (DRL) for robotics applications, it is important to find energy efficient motions, in which the standard method is to set an action penalty in the reward to find the optimal motion considering the energy expenditure (page 1, column 1). Naya et al. teaches this method is widely used for the simplicity of implementation, in which the reward is a linear sum (page 1, column 1). Naya et al. further teaches one standard way to obtain energy efficient behavior patterns by learning is to add an action penalty term to the reward function by multiplying the agent’s action by a weight coefficient for considering the energy expenditure; in which this method can be practically applied to any DRL algorithm because it only adds a term to the reward function, and it is reported to be effective in preventing overfitting (page 1, column 2). Therefore Naya et al. teaches the technique of including energy expenditure as a weight penalty within the linear sum reward calculation is a known, standard technique that can be applied to any reinforcement learning algorithm. Though Naya et al. teaches finding energy efficient motions is important for robotics applications, Lu et al. teaches energy efficiency is also an objective to closed-loop deep brain stimulation systems (page 7, column 2). Therefore, it would be obvious of one of ordinary skill in the art to apply this known technique of accounting for energy expenditure with reasonable expectation of success based on its simplicity and applicability within reinforcement learning algorithms . 07-21-aia AIA Claim s 6 and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Lu et al. (IDS filed 02/07/2023; NPL; cite no. 13: 2020), as applied to claims 1-4 and 11-14 previously, and in further view of Yao et al. (J Neural Eng; Vol. 18:3; March, 2021) . Claims 6 and 16 are directed to the feature values including: Hjorth parameters (activity mobility, and complexity indicators), beta band power, and sample entropy. Lu et al. teaches a method of using deep brain stimulation to treat Parkinson’s disease in which the reward parameter is calculated based on relay reliability, energy expenditure and discount factor penalties. Lu et al. further teaches to mitigate excessive beta oscillation, the reward function is modified as rt=−(pTAp+uTtBut) [eq. 27], where p indicates the power of beta oscillation, and further defining the power of the spike trains of STN neurons. Lu et al. does not teach feature values including Hjorth parameters. Yao et al. describes a method of predicting task performance from mental fatigue biomarkers in global brain activity. Yao et al. teaches extracting the following set of biomarkers from each electrocorticography (ECoG) channel (page 5, column 2): spectral power in multiple frequency bands, including high and low beta (page 6, table 1); wavelet entropy , which reflects the degree of order/disorder associated with a multi-frequency signal and has been shown to differentiate between different brain states (page 5, column 2); the Hjorth parameters indicating the statistical properties of neural signal in the time domain, including the Hjorth activity as a measure of signal variance, Hjorth mobility representing the mean frequency of a signal, and Hjorth complexity representing the frequency changes over time (page 5, column 2). Yao et al. teaches, the wavelet entropy features were highly discriminative for correct versus incorrect trials of NHP1 (page 8, column 1); and similarly, the Hjorth mobility is a highly discriminative feature for NHP2, where incorrect trials have a lower mobility compared to correct trials (page 8, column 1). Yao et al. further teaches the key to an effective closed-loop system will be the ability to robustly determine the onset or persistence of mental fatigue by analyzing brain activity in real-time (page 3, column 1); and this general approach was successful in closed-loop (or adaptive) stimulation strategies for epilepsy and movement disorders such as Parkinson’s (page 3, column 1). Therefore Yao et al. provides sufficient motivation for one of ordinary skill in the art to apply the highly discriminative feature values to the close-loop deep brain stimulation system with a reasonable expectation of success for the treatment of Parkinson’s disease . 07-21-aia AIA Claim s 7 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Lu et al. (IDS filed 02/07/2023; NPL; cite no. 13: 2020), as applied to claims 1-4 and 11-14 previously, in view of Fujimoto et al. (IDS filed 02/07/2023; NPL; cite no. 1: 2018) . Claims 7 and 17 are directed to the reinforcement learning module using a twin-delayed deep deterministic policy gradient (TD3) architecture. Lu et al. teaches a method of using deep brain stimulation to treat Parkinson’s disease in which the reward parameter is calculated based on relay reliability, energy expenditure and discount factor penalties. Lu et al. further teaches the reinforcement learning algorithm employs the actor-critic architecture to solve the closed-loop DBS control problems (page 5, column 2); and since the objective of critic is policy evaluation, temporal difference (TD) method are used as critic’s learning algorithm (page 6, column 1). Lu et al. does not teach using a twin-delayed deep deterministic policy gradient (TD3) architecture. Fujimoto et al. describes possible solutions to errors in actor-critic methods. Fujimoto et al. teaches overestimation bias and the accumulation of error in temporal difference methods are present in actor-critic settings (page 1, column 1); and a SARSA-style regularization technique which modifies the temporal difference target to bootstrap off similar state-action pairs (page 8, column 2), greatly improves both the learning speed and performance of DDPG in a number of challenging tasks in the continuous control setting, and exceeds the performance of numerous state of the art algorithms (page 8, column 2) define the Twin Delayed Deep Deterministic policy gradient algorithm (TD3). Fujimoto et al. further teaches these improvements and modifications are simple to implement and can be easily added to any other actor-critic algorithm (page 8, column 2). Therefore Fujimoto et al. provides sufficient motivation for one of ordinary skill in the art to improve a temporal difference method, within an actor critic algorithm by employing a twin-delayed deep deterministic policy gradient (TD3) architecture, with a reasonable expectation of success . 07-21-aia AIA Claim s 8-10 and 18-20 are rejected under 35 U.S.C. 103 as being unpatentable over Lu et al. (IDS filed 02/07/2023; NPL; cite no. 13: 2020) as applied to claims 1-4 and 11-14 previously, and in view of Brinda et al. (Springer; Feb, 2022) . Lu et al. teaches a method of using deep brain stimulation to treat Parkinson’s disease in which the reward parameter is calculated based on relay reliability, energy expenditure and discount factor penalties. Claims 8 and 18 are directed to the deep brain stimulation waveform being a biphasic pulse wave. Lu et al. does not teach the deep brain stimulation waveform being a biphasic pulse wave. Brinda et al. describes mechanisms and targeting of Deep-Brain Stimulation therapies. Brinda et al. teaches currents are delivered by most Deep-Brain Stimulation (DBS) systems as a biphasic stimulation waveform , with the first phase consisting of a narrow pulse (60–90 μs most often) followed by a longer duration secondary phase of opposite polarity that balances the charge injected in the first phase (page 8, column 1). Claims 9 and 19 are directed to a deep brain stimulator connected to the deep brain stimulation module and a subject brain; that can use the stimulation frequency and amplitude output as the deep brain stimulation waveform to generate a deep brain stimulation current corresponding to the deep brain stimulation waveform; and stimulate the subject brain with the deep brain stimulation current. Lu et al. further teaches DBS is a neurosurgical technique, which high-frequency mono-polar pulse trains are delivered via an implanted pulse generator and injected into areas of basal ganglia network (BG) through a surgically implanted electrode (page 1, column 1); and has been accepted as a well-documented and established neuromodulation method for the treatment of Parkinson’s disease (PD) (page 1, column 1). Claims 9 and 19 are further directed to a sensor connected to the feature extraction module and subject brain, that can sense the synaptic signal output from the subject brain; feature extraction module receiving the synaptic signal output from the sensor; extracting the feature values based on the synaptic signal; and the reinforcement learning module outputting the stimulation frequency and amplitude to the deep brain stimulation module using the trained deep brain stimulation neural network. Brinda et al. teaches feedback signals can be detected in the region of the stimulating electrodes as well as through sensors distal to that brain region or even external to the body (page 30, column 1); the closed DBS design that combines the stimulating and sensing interfaces in the same location has shown to be effective with STN-DBS in Parkinson’s Disorder (page 30, column 1); common anatomical targets for treating these cardinal motor signs with DBS include the STN and GPi (page 16, column 1); and responses of internal globus pallidus (GPi) model neurons to DBS amplitudes that are subthreshold and suprathreshold to generate action potentials directly within the model axons (page 12, fig. 4). Brinda et al. further teaches the clinical optimization of DBS settings, also known as programming, requires a substantial amount of clinical time to identify the most therapeutic electrode configurations and stimulation amplitudes, frequencies, and pulse widths (page 23, column 1); and recent efforts have integrated machine learning techniques, such as artificial neural networks into this approach to more efficiently predict the stimulation setting (page 26, column 1). Claims 10 and 20 are directed to the sensor being capable of sensing a brain cortical signal and thalamic action potential signal of the subject brain. Brinda et al. teaches recording sensors can also be placed distal to the stimulating electrodes, such as the use of cortical strip electrodes with clDBS(page 31, column 1); and the DBS lead target the dorsolateral subthalamic nucleus (STN) for treating Parkinson’s disease (page 5, fig. 2). Lu et al. further teaches the potential application of RL methods in future clinical DBS will consider much more factors, such as, which parameter (amplitude, frequency or pulse width) of DBS can be modulated, and how to train the neural network of RL controller using neurophysiological data before it is used to regulate stimulation directly (page 10, column 2). Therefore Brinda et al. teaches known methods of applying deep brain stimulation for use in treating a subject with Parkinson’s disease; and provides sufficient motivation for one of ordinary skill in the art to utilize neural networks in order to further improve the system. Lu et al. teaches an analogous brain stimulation system and reinforcement learning techniques that utilize a neural network in order to treat Parkinson’s more efficiently. As such, it would be obvious to one of ordinary skill in the art to combine the known methods of using the DBS systems with the reinforcement learning system methods taught by Lu et al. with a reasonable expectation of success. Conclusion No claims are currently allowed. Correspondence Any inquiry concerning this communication or earlier communications from the examiner should be directed to Milana Thompson whose telephone number is (571)272-8740. The examiner can normally be reached Monday - Friday, 9:00-6:00 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, Karlheinz Skowronek can be reached at (571) 272-1113. 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. /M.K.T./Examiner, Art Unit 1687 /Karlheinz R. Skowronek/Supervisory Patent Examiner, Art Unit 1687 Application/Control Number: 18/088,777 Page 2 Art Unit: 1687 Application/Control Number: 18/088,777 Page 3 Art Unit: 1687 Application/Control Number: 18/088,777 Page 4 Art Unit: 1687 Application/Control Number: 18/088,777 Page 5 Art Unit: 1687 Application/Control Number: 18/088,777 Page 6 Art Unit: 1687 Application/Control Number: 18/088,777 Page 7 Art Unit: 1687 Application/Control Number: 18/088,777 Page 8 Art Unit: 1687 Application/Control Number: 18/088,777 Page 9 Art Unit: 1687 Application/Control Number: 18/088,777 Page 10 Art Unit: 1687 Application/Control Number: 18/088,777 Page 11 Art Unit: 1687 Application/Control Number: 18/088,777 Page 12 Art Unit: 1687 Application/Control Number: 18/088,777 Page 13 Art Unit: 1687 Application/Control Number: 18/088,777 Page 14 Art Unit: 1687 Application/Control Number: 18/088,777 Page 15 Art Unit: 1687 Application/Control Number: 18/088,777 Page 16 Art Unit: 1687 Application/Control Number: 18/088,777 Page 17 Art Unit: 1687 Application/Control Number: 18/088,777 Page 18 Art Unit: 1687 Application/Control Number: 18/088,777 Page 19 Art Unit: 1687 Application/Control Number: 18/088,777 Page 20 Art Unit: 1687 Application/Control Number: 18/088,777 Page 21 Art Unit: 1687 Application/Control Number: 18/088,777 Page 22 Art Unit: 1687 Application/Control Number: 18/088,777 Page 23 Art Unit: 1687 Application/Control Number: 18/088,777 Page 24 Art Unit: 1687 Application/Control Number: 18/088,777 Page 25 Art Unit: 1687 Application/Control Number: 18/088,777 Page 26 Art Unit: 1687 Application/Control Number: 18/088,777 Page 27 Art Unit: 1687
Prosecution Insights