DETAILED ACTION
Response to Arguments
Applicant's amendment and arguments filed 06/27/2025, regarding the 35 USC 101 claim rejection have been fully considered and are persuasive. The 35 USC 101 rejection has been withdrawn.
Applicant's amendment and arguments filed 06/27/2025, regarding the 35 USC 103 claim rejections have been fully considered and are not persuasive
Regarding the 35 USC 103 rejection, Applicant argues “DiLorenzo only mentions environmental factors twice in its disclosure and neither of these two sections disclose, teach or suggest providing therapy modification recommendations based on the environmental factor”. The Examiner respectfully disagrees. DiLorenzo discloses that the environmental factor is used to quantify therapy efficacy and then adjust therapy based on the efficacy (par. [0029, 0170]), wherein therapy is not limited to only pharmacological treatment, but can also involve electrical stimulation (par. [0062], “Advantageously, the methods and system of the present invention allow a physician to customize the information or recommendations provided to the patient. Certain patients may benefit from certain actions, when performed in a timeframe preceding a seizure. For example, the appropriate action is typically in the form of electrical stimulation or manual or automatic delivery of a pharmacological agent”, (emphasis added)). DiLorenzo further discloses that the electrical stimulation can be to a cranial nerve such as the vagus nerve (par. [0023, 0072, 0111]).
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103(a) which forms the basis for all obviousness rejections set forth in this Office action:
(a) A patent may not be obtained though the invention is not identically disclosed or described as set forth in section 102 of this title, if the differences between the subject matter sought to be patented and the prior art are such that the subject matter as a whole would have been obvious at the time the invention was made to a person having ordinary skill in the art to which said subject matter pertains. Patentability shall not be negatived by the manner in which the invention was made.
Claims 1-3, 7, 9, 11-14 are rejected under 35 U.S.C. 103(a) as being unpatentable over DiLorenzo (2007/0287931).
Regarding Claims 1, 7, 9, 11 and 12, DiLorenzo discloses a method for assessing the efficacy of applied epilepsy treatment (par. [0025, 0061]) comprising selecting, using device 12, a plurality of dependent variables (e.g. EEG readings, temperature readings, biochemical data, and other physiological signals) relating to a plurality of seizures in a patient (Fig. 2; par. [0065, 0090]); selecting, using device 12, a plurality of independent variables (e.g. patient input data) comprising therapy parameters (i.e. type of applied medications), therapy delivery parameters (dosing of medications), temporal factors (i.e. timing of drug doses), environmental factors and/or patient factors (i.e. patient state or well-being) (Fig. 2; par. [0066, 0095, 0098]); quantifying relationships between dependent and independent variables using classifier 64 (par. [0095, 0098]); and performing an action with an algorithm of system 10 in response to the determined quantified relationships, such as changing therapy (which involves therapy recommendations), applying therapy, reporting a patient condition (such as an adverse effect which could include lack of reduction in the likelihood of a seizure), assessing efficacy of therapy and whether changes need to be made to therapy, etc. (par. [0104, 0111, 0114, 0132]). More specifically, DiLorenzo discloses that the environmental factor is used to quantify therapy efficacy and then adjust therapy based on the efficacy (par. [0029, 0170]), wherein therapy is not limited to only pharmacological treatment, but can also involve electrical stimulation (par. [0062], “Advantageously, the methods and system of the present invention allow a physician to customize the information or recommendations provided to the patient. Certain patients may benefit from certain actions, when performed in a timeframe preceding a seizure. For example, the appropriate action is typically in the form of electrical stimulation or manual or automatic delivery of a pharmacological agent”, (emphasis added)). DiLorenzo further discloses that the electrical stimulation can be to a cranial nerve such as the vagus nerve (par. [0023, 0072, 0111]).
DiLorenzo fails to disclose using the claimed independent variables and only the independent variables as presently claimed and argued. However, DiLorenzo discloses any combination of these variables can be utilized in the predictive model (par. [0095]) which mimics the language from Applicant’s originally filed disclosure, see par. [0040, 0066] of PGPUB 2019/0328262, which is the publication of the present application). Applicant has not asserted any criticality to using only the parameters claimed and has not attributed any unexpected results to using only the variables claimed.
Therefore, the Examiner notes it would have been obvious to one of ordinary skill in the art before the invention was made to try and use the claimed variables and the claimed number and pairing of dependent and independent variables as inputs to the predictive model since DiLorenzo discloses these parameters and there are a finite number of identified, predictable solutions, each with a reasonable expectation of success. This is a routine optimization problem of finding the best parameters/combination of parameters from a known list of parameters already used for seizure prediction to most accurately predict seizure activity.
In regards to Claim 2, DiLorenzo discloses quantifying and ranking the dependent and independent variables as vectors, which are defined by a magnitude and direction. Furthermore, DiLorenzo discloses that the variables can be quantified and ranked as scalars, which are solely defined by a magnitude (par. [0098]).
With regards to Claim 3, DiLorenzo discloses storing in memory the quantified relationships for display and/or future use and discloses storing historical data in memory related to the variables of interest
Regarding Claims 13 and 14, DiLorenzo discloses applying therapy using an electrostimulation generator or drug dispenser (par. [0023, 0074, 0114]).
Claims 4 and 5 are rejected under 35 U.S.C. 103(a) as being unpatentable over DiLorenzo (2007/0287931) in view of Kovach et al. (2009/0082640) further in view of Huang et al. “Kernel Based Algorithms for Mining Huge Data Sets “).
Regarding Claims 4 and 5, DiLorenzo discloses using data inputs related to seizure activity to predict a future occurrence of a seizure and to assess the efficacy of applied treatment but does not disclose using the particular dependent variables set forth in the claims.
However, Kovach discloses that dependent variables such as seizure occurrence, which is a record of seizure frequency (par. [0080]) or seizure duration (par. [0100]), are known parameters to assess efficacy of seizure therapy. Taking known data previously used by a physician to make decisions and integrating it into an automated algorithm to mimic human thought, i.e. machine learning, is an obvious automation step and one of ordinary skill in the art would appreciate that any number of known data inputs that have been established to be indicative of a particular behavior or beneficial to tracking a particular behavior would be a beneficial data point to include in a machine learning algorithm that is designed to predict/track that particular behavior, which in this case would be seizure progression and therapy efficacy.
Additionally, Huang discloses the progression of technology to use machine learning processes in lieu of relying on human decision making due to the increasing amount of data points that can be used to quantify an output and the benefit in speed an robustness that machines have in streamlining the processing of large amounts of data (Preface; pp. 1-4).
In summary, the feature vectors (dependent variables claimed) are not new/previous unknown data points that can be used to track and treat seizures and Applicant has not created any new types of learning algorithms to utilize this data to track and treat seizures. The claims merely replace a process that has been typically done by a physician (see the disclosure of Kovach) with an automated learning/prediction process, which is well-known in the art as machine learning, and in particular supervised machine learning. As such, the claims merely amount to a generic and known automation process for steps previously done manually and or mentally by a human (see also MPEP §2144.04, III).
Therefore it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the device in the DiLorenzo reference to include dependent variables such as seizure occurrence, which is a record of seizure frequency, or seizure duration as taught and suggested by Kovach, and to feed this data to a predictive machine learning algorithm, as taught and suggested by Huang, for the purpose of providing quick, efficient and robust way to automatically predict/track seizure activity and therapy efficacy.
Claims 1 and 8-14 are rejected under 35 U.S.C. 103(a) as being unpatentable over Kovach et al. (2009/0082640) in view of DiLorenzo (2007/0287931), further in view of McMaster University (WO 2009/103156), herein McMaster.
Regarding Claims 1 and 8-10, Kovach discloses assessing the efficacy of an applied epilepsy therapy (Abstract; par[ 0046]) comprising selecting a plurality of dependent variables (e.g. physiological parameters) relating to a plurality of seizures (par. [0069, 0080]) and selecting a plurality of independent variables such as therapy parameters (type of drug taken), therapy delivery parameters (dosage of drug taken), a temporal factor (time of event), an environmental factor (body temperature) and a patient factor (patient input data), see par. [0073, 0080]). Kovach further discloses that the clinician reviews the variable and their relationships in order to determine the efficacy of treatment (par. [0046, 0081), wherein a lack of improvement or further identification of symptoms can be considered assessing an adverse effect of therapy, and then makes therapy recommendations or changes to therapy, such as electrical stimulation therapy (par. [0005]), based on the evaluation (par. [0081]). Kovach is silent regarding targeting a cranial nerve and is silent regarding using the claimed independent variables and only the independent variables as presently claimed and argued and is silent regarding automating the quantifying process.
However, Kovach discloses any combination of these variables can be utilized in the prediction (par. [0080-0081]) which mimics the language from Applicant’s originally filed disclosure, see par. [0040, 0066] of PGPUB 2019/0328262, which is the publication of the present application). Applicant has not asserted any criticality to using only the parameters claimed and has not attributed any unexpected results to using only the variables claimed.
Therefore, the Examiner notes it would have been obvious to one of ordinary skill in the art before the invention was made to try and use the claimed variables and the claimed number/combination of dependent and independent variables as predictive factors since Kovach discloses these parameters and there are a finite number of identified, predictable solutions, each with a reasonable expectation of success. This is a routine optimization problem of finding the best parameters/combination of parameters from a known list of parameters already used for seizure prediction to most accurately predict seizure activity.
Furthermore, DiLorenzo discloses that cranial nerve stimulation (such as vagus nerve stimulation) is a known equivalent stimulation regiment to that of drug therapy, DBS therapy etc. typically used for seizure treatment (par. [0023]) that provides a benefit such as a less invasive procedure (neck access versus brain access and implantation)as compared to DBS therapy).
Therefore, it would have been obvious to one having ordinary skill in the art before the invention was made to modify the device of Kovach to include vagal nerve stimulation (VNS) as the particular epilepsy therapy, as taught and suggested by DiLorenzo since it was a known equivalent to drug therapy and DBS therapy as well as providing the benefit of a less invasive therapeutic procedure.
Additionally, McMaster discloses reducing wait times for diagnoses and improving the efficiency and accuracy of prediction and estimation models (pp.1-4) by using linear models (of which linear regression is a subset) (pp. 24-26), which are executed by a computer (i.e. device with a processor). In other words, the automation of diagnostic and estimation procedures in the field of mental and neurological disorders (McMaster, Abstract) is known in the art.
Therefore it would have been obvious to one of ordinary skill in the art at the time the invention was made to modify the device in the Kovach reference to include a machine learning process that uses linear models, as taught and suggested by McMaster, for the purpose of reducing wait times for diagnoses and improving the efficiency and accuracy of prediction and estimation models.
In regards to Claim 11, Kovach discloses obtaining a body signal, such as an EEG signal (par. [0041]), using a sensor (par. [0069, 0080]).
With regards to Claim 12, Kovach discloses a sensor (e.g. patient programmer 24) that receives input relating to event information 50 (par. [0080]).
In regards to Claims 13 and 14, Kovach discloses applying electrical therapy or drug therapy with a therapy delivery system (par. [0031]).
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ALLEN PORTER whose telephone number is (571)270-5419. The examiner can normally be reached Mon - Fri 9:00-6:00 EST.
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, Carl Layno can be reached at 571-272-4949. 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.
/ALLEN PORTER/Primary Examiner, Art Unit 3796
Prosecution Insights