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 .
Response to Arguments
Applicant’s arguments filed 05/26/2026 have been fully considered but are moot in view of a new grounds of rejection or are not persuasive.
Applicant argues, “claim 1 recites one or more elements that cannot be practically performed in the human mind…The claim recites implanting a physical cortical interface device at a motor cortex of a patient. The method also recites decoding brain signals recorded by an electrode array by a machine learning algorithm trained to decode an imagined performance of an action. Further, the method recites calibrating the trained machine learning model based on recorded brain signals from a patient to generate a personalized version of the machine learning model specific to the patient. Finally, a communication channel is established with the patient that includes displaying a communication state on a user interface. None of these limitations can be performed in the human mind.”
Examiner respectfully states the following limitations,
implanting the cortical interface device at a region of a motor cortex of the patient;
calibrating a machine learning model trained on recorded brain signals to decode an imagined performance of an action using the recorded first brain signals from the patient to generate a personalized version of the machine learning model specific to the patient that decodes whether the patient is imagining performance of an action;
initiating decoding of the recorded brain signals via the personalized machine learning model;
recording, via the cortical interface device, second brain signals;
initiating decoding of the second brain signals via the personalized machine learning model; and
establishing a communication channel with the patient by displaying, via a user interface, a communication state of the patient based on the results of the decoded second brain signals
the cortical interface comprising an electrode array for recording neural signals from the cortical surface
a computer system communicably coupled to the cortical interface,
the computer system comprising a user interface, a processor, and a memory,
are interpreted as additional elements.
Furthermore, Examiner asserts that the above recited limitations are directed to pre-solution activities (see MPEP 2106.05(g)), because they’re used to obtain additional information used to communicate with the patient.
Additionally, the limitation, “establishing a communication channel with the patient by displaying, via a user interface, a communication state of the patient based on the results of the decoded second brain signals”, is directed to insignificant post solution activity (see MPEP 2106.05(g)).
The above recited limitations merely process information and then display the results of the above identified abstract ideas. Additionally, the recited “displaying” is neither particular enough to meaningfully limit the recited exception nor does it have more than a nominal relationship to the exception. In other words, the breadth of the recited “displaying” is such that it substantially encompasses all applications of the recited exception (such as moving information).
There is nothing in the claims which show how displaying a communication state of the patient integrates the judicial exception into a practical application.
Further, Examiner asserts that the limitations are not particular and instead provide instructions to apply the exception in a generic way (see factor ‘a’ in MPEP §2106.04(d)(2)). There is nothing in the claim which shows how establishing a communication channel particularly and specifically treats a particular disorder, or integrates the abstract idea into a practical application.
Moreover, there is no evidence of record that would support the assertion that this step is an improvement to a computer or a technological solution to a technological problem.
Regarding the limitations, “via a user interface” and “via the personalized machine learning model,” Examiner asserts that the recited limitations amount to nothing more than mere instructions to apply the abstract idea using a generic computer (MPEP 2106.05(f), Alice Corp., 573 U.S. at 223, 110 USPQ2d at 1983).
Additionally, the above recited claims’ recitation of a machine learning model and a computer system comprising a user interface, a processor, and a memory that stores instructions are merely reciting the computer components at a high-level of generality. In other words, the computer components are being used as a tool to carry out the system’s functions (See MPEP 2106.05(f)).
Applicant argues, “Such analysis should be performed by identifying additional elements that go beyond the alleged judicial exceptions and evaluating those elements individually and in combination to determine whether they integrate the alleged exception into a practical application. See MPEP 2106.04(d)(I). The evaluation must consider even those elements the Office deems well-understood, routine, and conventional." See id. Indeed, even 'well-understood, routine and conventional' limitations, when used in combination with judicial exceptions, may nonetheless provide a practical application of concepts deemed to be judicial exceptions. See id.”
Examiner respectfully states that, regarding the following limitations:
“implanting the cortical interface device at a region of a motor cortex of the patient;
the cortical interface comprising an electrode array for recording neural signals from the cortical surface;
a machine learning model
a computer system communicably coupled to the cortical interface,
the computer system comprising
a user interface,
a processor, and
a memory”,
see Ayyad (US 2020/0187841), which discloses a system [0006] for measuring a user’s perceptual experience [0006, 0035]
implanting ([0051]: invasive i.e. implanted sensors measure EEG signals; [0273]) a cortical interface device (fig. 3; [0057]: motor cortical areas) at a region of a motor cortex of a patient [0057, 0208];
the cortical interface comprising an electrode array (fig. 3; [0057]) for recording neural signals from a cortical surface [0057];
a machine learning model [0060],
a computer system ([0009]: a processing system) communicably coupled to the cortical interface ([0007]: processing system comprises deep learning module that receives and processes signals; [0051, 0057]),
the computer system comprising
a user interface ([0062]: EEG used to measure body part, body language, and physical activity; [0050]: gestures can be used to control user interface so the computer system must be contacted to a user interface so the user can control it based on recorded EEG; [0166]),
a processor [0009], and
a memory [0009].
Thus, the limitations directed to a cortical interface device, a machine learning model, a computer system communicably coupled to the cortical interface and comprising a user interface, a processor, and a memory are well-understood, routine, and conventional, as evidenced by the reference above.
Applicant argues, “Such a process certainly goes beyond merely a mental process and is rather directed to a practical application of implanting a cortical interface device, calibrating a trained machine learning to generate a personalized version of the model specific to the patient that decodes recorded brain signals to determine whether the patient is imagining performance of an action, decodes the recorded brain signals using the personalized model, and establishes a communication channel that includes displaying results on a user interface.”
Examiner respectfully disagrees. As stated above, there is nothing in the claims which show how displaying a communication state of the patient integrates the judicial exception into a practical application. Further, the recited limitations amount to nothing more than mere instructions to apply the abstract idea using a generic computer (MPEP 2106.05(f), Alice Corp., 573 U.S. at 223, 110 USPQ2d at 1983).
Thus, the abstract idea is not integrated into a practical application and the combination of these additional elements is no more than insignificant extra solution activity, and generic computer components.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-12 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception, specifically an abstract idea without significantly more.
Step 1:
Independent claims 1, 7, and 12 are directed a computer implemented method, computer-implemented method, and a system for communicating with a patient that is clinically unresponsive via a cortical interface device, respectively. Thus, they are directed to statutory categories of invention.
Step 2A, Prong 1:
Claims 1, 7, and 12 recite the following claim limitations which are directed to abstract ideas, specifically organizing human activity and mental processes (see MPEP § 2106.04(a)(2)):
In re claim 1:
guiding the patient through a training exercise while recording first brain signals via the cortical interface device (organizing human activity by guiding patient through an activity);
determining, based on the recorded first brain signals indicating the motor cortex responding to the training exercise, that the patient has cognitive motor dissociation (CMD) (mental process – person can look at the brain signals and decide that a patient in a coma is conscious and able to understand verbal commands);
determining the performance of the personalized machine learning model is greater than a threshold (mental process – person can determine whether the personalized machine learning model is performing better than a threshold);
instructing the patient to imagine performing a motor function (organizing human activity – person communicating with patient based on results).
In re claim 7, see above.
In re claim 12, see above.
These limitations, under their broadest reasonable interpretation, cover concepts that can be practically performed in the human mind, as well as concepts that involve organizing human activity and mathematical concepts.
Therefore, the claim limitations fall within the mental processes and organizing human activity groupings of abstract ideas.
Step 2A, Prong 2:
Claims 1, 7 and 12 recite the following additional elements:
In re claim 1,
implanting the cortical interface device at a region of a motor cortex of the patient;
calibrating a machine learning model trained on recorded brain signals to decode an imagined performance of an action using the recorded first brain signals from the patient to generate a personalized version of the machine learning model specific to the patient that decodes whether the patient is imagining performance of an action;
initiating decoding of the recorded brain signals via the personalized machine learning model;
recording, via the cortical interface device, second brain signals;
initiating decoding of the second brain signals via the personalized machine learning model; and
establishing a communication channel with the patient by displaying, via a user interface, a communication state of the patient based on the results of the decoded second brain signals.
In re claim 7, see above as well as the following limitations:
the cortical interface comprising an electrode array for recording neural signals from the cortical surface
a computer system
In re claim 12, see above as well as the following limitations:
a computer system communicably coupled to the cortical interface,
the computer system comprising a user interface, a processor, and a memory.
The following limitations:
“calibrating a machine learning model trained on recorded brain signals to decode an imagined performance of an action using the recorded first brain signals from the patient to generate a personalized version of the machine learning model specific to the patient that decodes whether the patient is imagining performance of an action;
initiating decoding of the recorded brain signals via the personalized machine learning model;
recording, via the cortical interface device, second brain signals;
initiating decoding of the second brain signals via the personalized machine learning model”,
are pre-solution activities (see MPEP 2106.05(g)), because they’re used to obtain additional information used to communicate with the patient.
Additionally, the limitation, “establishing a communication channel with the patient by displaying, via a user interface, a communication state of the patient based on the results of the decoded second brain signals”, is directed to additional elements, specifically insignificant post solution activity (see MPEP 2106.05(g)).
The above recited limitations merely process information and then display the results of the above identified abstract ideas. Additionally, the recited “displaying” is neither particular enough to meaningfully limit the recited exception nor does it have more than a nominal relationship to the exception. In other words, the breadth of the recited “displaying” is such that it substantially encompasses all applications of the recited exception (such as moving information).
There is nothing in the claims which show how displaying a communication state of the patient integrates the judicial exception into a practical application.
Further, Examiner asserts that the limitations are not particular and instead provide instructions to apply the exception in a generic way (see factor ‘a’ in MPEP §2106.04(d)(2)). There is nothing in the claim which shows how establishing a communication channel particularly and specifically treats a particular disorder, or integrates the abstract idea into a practical application.
Moreover, there is no evidence of record that would support the assertion that this step is an improvement to a computer or a technological solution to a technological problem.
Regarding the limitations, “via a user interface” and “via the personalized machine learning model,” Examiner asserts that the recited limitations amount to nothing more than mere instructions to apply the abstract idea using a generic computer (MPEP 2106.05(f), Alice Corp., 573 U.S. at 223, 110 USPQ2d at 1983).
Additionally, the above recited claims’ recitation of a machine learning model and a computer system comprising a user interface, a processor, and a memory that stores instructions are merely reciting the computer components at a high-level of generality. In other words, the computer components are being used as a tool to carry out the system’s functions (See MPEP 2106.05(f)).
Thus, the abstract idea is not integrated into a practical application. The combination of these additional elements is no more than insignificant extra solution activity, and generic computer components. Accordingly, even in combination, these additional elements do not integrate the abstract idea into a practical application. The claim is directed to an abstract idea.
Step 2B:
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
Additionally, regarding the limitations:
“implanting the cortical interface device at a region of a motor cortex of the patient;
the cortical interface comprising an electrode array for recording neural signals from the cortical surface;
a machine learning model
a computer system communicably coupled to the cortical interface,
the computer system comprising
a user interface,
a processor, and
a memory”,
see Ayyad (US 2020/0187841), which discloses a system [0006] for measuring a user’s perceptual experience [0006, 0035]
implanting ([0051]: invasive i.e. implanted sensors measure EEG signals; [0273]) a cortical interface device (fig. 3; [0057]: motor cortical areas) at a region of a motor cortex of a patient [0057, 0208];
the cortical interface comprising an electrode array (fig. 3; [0057]) for recording neural signals from a cortical surface [0057];
a machine learning model [0060],
a computer system ([0009]: a processing system) communicably coupled to the cortical interface ([0007]: processing system comprises deep learning module that receives and processes signals; [0051, 0057]),
the computer system comprising
a user interface ([0062]: EEG used to measure body part, body language, and physical activity; [0050]: gestures can be used to control user interface so the computer system must be contacted to a user interface so the user can control it based on recorded EEG; [0166]),
a processor [0009], and
a memory [0009].
Thus, the limitations directed to a cortical interface device, a machine learning model, a computer system communicably coupled to the cortical interface and comprising a user interface, a processor, and a memory are well-understood, routine, and conventional, as evidenced by the reference above.
As discussed with respect to Step 2A Prong Two, the additional elements in the claim amount to no more than insignificant extra solution activity and generic computer components.
The same analysis applies here in 2B and does not provide an inventive concept.
Therefore, none of the claims 1-16 amount to significantly more than the abstract idea itself. Accordingly, claims 1-16 are not patent eligible and rejected under 35 U.S.C. 101 as being directed to abstract ideas implemented on a generic computer in view of the Supreme Court Decision in Alice Corporation Pty. Ltd. v. CLS Bank International, et al. and 2019 PEG.
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.
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.
Claims 1-3 and 5-16 are rejected under 35 U.S.C. 103 as being unpatentable over Colachis et al. US 2023/0062326) in view of NPL “Cognitive motor dissociation to predict time to functional recovery in patients with acute brain injury” (hereinafter referred to as “Egbebike”) in view of Alcaide et al. (US 2020/0192478) in view of Patak et al. (US 2015/0213214).
In re claim 1, Colachis discloses a method [0007] for communicating with a patient that is clinically unresponsive ([0021]: patient unable to control his or her own muscles) via a cortical interface device [0019], the method comprising:
implanting the cortical interface device at a region of a motor cortex of the patient ([0043]: implanted electrodes measure neural activity; [0019]: cortical implant; [0022]: rebuilds motor cortex);
guiding the patient through a training exercise ([0027]: instructions for performing sequence of actions; [0025]: CNN used during training to identify when promoted action is complete) while recording first brain signals via the cortical interface device ([0031]: EEG electrodes from a skullcap measure brain neural activity measurement and acquire EEG signals; [0019]);
determining, based on the recorded first brain signals indicating the motor cortex responding to the training exercise, that the patient is imagining performing an action ([0034]: brain neural activity is used to determine intent of an action),
calibrating a machine learning model [0025, 0043] trained on recorded brain signals to decode an imagined performance of an action ([0043]: support vector machine is trained to receive rain neural activity and decode an intended action) using the recorded first brain signals from the patient [0043] to generate a version of the machine learning model that decodes whether the patient is imagining performance of an action ([0034]: brain neural activity measured to determine intent to manipulate an object; [0043]: machine learning receives brain neural activity from surface electrodes of the skullcap and decodes an intended action; [0048]);
initiating decoding of the recorded brain signals [0019] via the machine learning model [0043];
determining the performance of the machine learning model is greater than a threshold ([0043]: machine learning model is cable of decoding the intended action, i.e. it must exhibit at least a threshold performance in decoding);
instructing the patient to imagine performing a motor function ([0027]: providing instructions requires person P to imagine performing a motor function; [0019]: intended movement must be imagined);
recording, via the cortical interface device, second brain signals ([0024]: closed loop rehabilitation training platform is used which would provide second brain signals);
initiating decoding of the second brain signals via the machine learning model (([0024]: closed loop rehabilitation training platform would result in the second brain signals being decoded via the machine learning model); and
communicating with the patient based on the results of the decoded second brain signals ([0019]: FES is delivered to effectively implement the intended movement; [0024]: closed-loop rehabilitation training platform).
Colachis fails to disclose
determining, based on the recorded first brain signals indicating the motor cortex responding to the training exercise, that the patient has cognitive motor dissociation (CMD)
calibrating a machine learning trained on recorded brain signals to decode an imagined performance of an action using the recorded first brain signals from the patient to generate a personalized version of the machine learning model specific to the patient that decodes whether the patient is imagining performance of an action;
initiating decoding of the recorded brain signals via the personalized machine learning model;
determining the performance of the personalized machine learning model is greater than a threshold;
initiating decoding of the second brain signals via the personalized machine learning model; and
establishing a communication channel with the patient by displaying, via a user interface, a communication state of the patient based on the results of the decoded second brain signals.
Egbebike teaches predicting time to recovery in acutely brain injured patients (pg. 1: Background, lines 1-4) and teaches providing spoken commands to patients with brain injury (pg. 9, Recovery trajectory, lines 1-11), and that CMD diagnosis is provided (pg. 9, Recovery trajectory, lines 1-11) using machine learning applied to EEG recordings (pg. 1, Summary, lines 1-10).
Egbebike further teaches that diagnosis of CMD provides more precise counseling for families of unresponsive patients (pg. 2, Interpretation, lines 1-4; pg. 2) and identifies patients that benefit from rehabilitation (pg. 2, Interpretation, lines 1-4; pg. 2, Findings, lines 1-7).
It would have been obvious to someone of ordinary skill in the art at the time the instant invention was filed to modify the method for communicating with a patient that is clinically unresponsive taught by Colachis, to provide determining, based on the recorded first brain signals indicating the motor cortex responding to the training exercise, that the patient has cognitive motor dissociation (CMD), as taught by Egbebike, because CMD diagnosis provides more precise counseling for families of unresponsive patients and identifies patients that benefit from rehabilitation.
Regarding the limitations
“calibrating a machine learning trained on recorded brain signals to decode an imagined performance of an action using the recorded first brain signals from the patient to generate a personalized version of the machine learning model specific to the patient that decodes whether the patient is imagining performance of an action;
initiating decoding of the recorded brain signals via the personalized machine learning model;
determining the performance of the personalized machine learning model is greater than a threshold;
initiating decoding of the second brain signals via the personalized machine learning model”,
Alcaide teaches a brain computer interface (BCI) platform [0006] to track brain activity [0006] to track real-time positioning of a user's gaze or attention and activation of a desired action [0006] and teaches
calibrating a machine learning ([0080]: tailoring a model to a patient; [0082]) trained on recorded brain signals to decode an imagined performance of an action using the recorded brain signals from a patient to generate a personalized version of the machine learning model specific to the patient ([0080]: training environment is provided to a user to build statistical models that are tailored to that patient) that decodes whether the patient is imagining performance of an action ([0082]: trainer is used to build the model and then use a statistical tool to generate predictions of user behavior and estimating user intent i.e. decoding an imagined performance of the user from brain data);
initiating decoding of the recorded brain signals via the personalized machine learning model [0080-0082];
determining the performance of the personalized machine learning model ([0080]: personalized models can be tested and cross-validated with new data);
initiating decoding of the second brain signals via the personalized machine learning model ([0080]: models are tested using new brain data from the user).
Alcaide further teaches that models can be built, tested and cross-validated [0080] from that particular user to achieve a high accuracy and speed of interaction [0080].
It would have been obvious to someone of ordinary skill in the art at the time the instant invention was filed to modify the method for communicating with a patient that is clinically unresponsive yielded by the proposed combination, to provide calibrating a machine learning trained on recorded brain signals to decode an imagined performance of an action using the recorded first brain signals from the patient to generate a personalized version of the machine learning model specific to the patient that decodes whether the patient is imagining performance of an action; initiating decoding of the recorded brain signals via the personalized machine learning model; determining the performance of the personalized machine learning model is greater than a threshold; initiating decoding of the second brain signals via the personalized machine learning model, as taught by Alcaide, because models can be built, tested and cross-validated from a particular user to achieve a high accuracy and speed of interaction.
Regarding the limitations, “establishing a communication channel with the patient by displaying, via a user interface, a communication state of the patient based on the results of the decoded second brain signals”, Patak teaches a computer implemented method [0003] for facilitating communication between a patient and a family member [0003], and teaches establishing a communication channel with the patient ([0048]: patient can select an object that will automatically generate a phrase in a text box; [0009]: patient may electronically select an object using eye gaze technology) by displaying, via a user interface (fig. 2: 10), a communication state of the patient based on the results of decoded signals ([0056]: generated sentence may be displayed on screen based on what a patient was intending on saying; [0048]: sentences are automatically generated based on object selected by patient, which are interpreted as decoded signals).
Patak further teaches that displaying the sentence allows a patient’s family, friends, and caregivers to all understand what the patient is wanting to say [0056, 0061].
It would have been obvious to someone of ordinary skill in the art at the time the instant invention was filed to modify the method for communicating with a patient that is clinically unresponsive yielded by the proposed combination, to provide establishing a communication channel with the patient by displaying, via a user interface, a communication state of the patient based on the results of the decoded second brain signals, as taught by the decoding of intended communication of Patak being displayed, because doing so will allow a patient’s family, friends, and caregivers to all understand what the patient is wanting to say.
In re claim 2, the proposed combination yields (all mapping directed to Colachis unless otherwise stated) further comprising: determining, based on the recorded brain signals, that the motor cortex of the patient is responding to the training exercise ([0034]: brain neural activity is decoded to determine intent to manipulate object).
In re claim 3, the proposed combination yields (all mapping directed to Colachis unless otherwise stated) wherein
the cortical interface device is a first cortical interface device ([0007]: first subset of electrodes) and the region of the motor cortex is a first region of the motor cortex ([0007]: position where first subset of electrodes are placed),
the method further comprising: placing a second cortical interface device ([0007]: second subset of electrodes) at a second region of the motor cortex of the patient ([0007]: position where second subset of electrodes are placed).
In re claim 5, the proposed combination yields (all mapping directed to Colachis unless otherwise stated) wherein the motor function comprises squeezing a hand ([0023]: intended action may be grabbing an object i.e. squeezing a hand) or throwing an object.
In re claim 6, the proposed combination yields (all mapping directed to Colachis unless otherwise stated) wherein the motor function is associated with a binary response ([0019]: binary response is whether there is an intended action or not; [0034]).
In re claim 7, the proposed combination yields (all mapping directed to Colachis unless otherwise stated)
a computer-implemented method [0027] for communicating with a patient that is clinically unresponsive using a cortical interface device surgically implanted adjacent to a motor cortex at a cortical surface of the patient (see in re claim 1 above),
the cortical interface (see in re claim 1 above) comprising an electrode array [0019] for recording neural signals from the cortical surface ([0019]: electrodes measure neural signals and cortical implant can be used; [0043]: implanted electrodes can be used; [0031]),
the method comprising:
receiving, by a computer system, first brain signals from the cortical interface device [0043],
wherein the first brain signals correspond to an action being imagined by the patient (see in re claim 1 above),
wherein the action corresponds to the motor cortex [0022];
calibrating, by the computer system, a machine learning model [0025] trained on recorded brain signals to decode an imagined performance of an action (see in re claim 1 above) using the received first brain signals from the patient to generate a personalized version of the machine learning model specific to the patient (see the proposed combination yielded in re claim 1 above) that decodes the action ([0034]: brain neural activity measured to determine intent to manipulate an object; [0043]: machine learning used to receive brain neural activity and decode an intended action; [0048]);
initiating decoding of the recorded first brain signals via the personalized machine learning model (see the proposed combination yielded in re claim 1 above);
determining, by the computer system, whether the personalized machine learning model exhibits at least a threshold performance in decoding the action ([0043]: machine learning model is cable of decoding the intended action, i.e. it must exhibit at least a threshold performance in decoding; see also the proposed combination yielded in re claim 1 above);
record, via the cortical interface device, second brain signals (see in re claim 1 above)
initiating decoding of the recorded first brain signals via the personalized machine learning model (see in re claim 1 above);
in response to the personalized machine learning model exhibiting at least the threshold performance, indicating, by the computer system, via a user interface ([0029]: user interface is combination of electrical stimulation and determination 36 of NES stimulation pattern, which communicates with a user [0033]; [0023]: stimulation adjusted based on sensor feedback), whether the patient is imagining the action based on the decoded second brain signals ([0006]: stimulation pattern is applied to cause body part to perform the intended action, therefore the stimulation pattern being applied means the patient must imagine the action).
Regarding the limitations, “determining, by the computer system, that the patient has cognitive motor dissociation (CMD) based on the correspondence of the first brain signals and the action”, see the proposed combination yielded in re claim 1 above.
In re claim 8, the proposed combination yields (all mapping directed to Colachis unless otherwise stated) wherein the training, by the computer system, the personalized machine learning model on the received brain signals to decode the action comprises transfer learning ([0048]: determining hand-object relationship may partially rely on CNN i.e. transfer learning that is trained to detect the person’s hand; [0034]: brain neural activity may be decoded to determine intent).
In re claim 9, regarding the limitations, “wherein the cortical interface device is a first cortical interface device, the region of the motor cortex is a first region of the motor cortex, and the brain signals are first brain signals, the computer-implemented method further comprising: receiving second brain signals from a second cortical interface device at a second region of the motor cortex of the patient”, see in re claim 3 above.
In re claim 10, regarding the limitations, “wherein the action comprises squeezing a hand or throwing an object”, see in re claim 5 above.
In re claim 11, regarding the limitations, “wherein the action is associated with a binary response”, see in re claim 6 above.
In re claim 12, Colachis discloses a system [0006] for communicating with a patient that is clinically unresponsive (see in re claim 1 above), the system comprising:
a cortical interface device to be surgically implanted at a motor cortex at a cortical surface of the patient (see in re claim 1 above),
the cortical interface comprising an electrode array for recording neural signals from the cortical surface (see in re claim 7 above); and
a computer system [0066] communicably coupled to the cortical interface ([0066]: non-transitory storage medium performs action 40; [0034]: operation 40 involves determining intent to manipulate the object; [0019]),
the computer system comprising
a user interface (see in re claim 7 above),
a processor [0033, 0040], and
a memory [0066].
Regarding the limitations,
“the memory storing instructions that, when executed by the processor, cause the computer system to: receive first brain signals from the cortical interface device,
wherein the first brain signals correspond to an action being imagined by the patient,
wherein the action corresponds to the motor cortex;
determining, by the computer system, that the patient has cognitive motor dissociation (CMD) based on the correspondence of the first brain signals and the action;
calibrate a machine learning model trained on recorded brain signals to decode an imagined performance of an action using the received first brain signals from the patient to generate a personalized version of the machine learning model specific to the patient that decodes the action;
initiate decoding of the recorded first brain signals via the personalized machine learning model;
determine whether the personalized machine learning model exhibits at least a threshold performance in decoding the action; and
record, via the cortical interface device, second brain signals;
initiating decoding of the second brain signals via the personalized machine learning model
in response to the personalized machine learning model exhibiting at least the threshold performance, indicate, via the user interface, whether the patient is imagining the action based on the decoded second brain signals”,
see in re claim 7 above.
In re claim 13, Colachis discloses wherein the personalized machine learning model comprises a convolutional neural network ([0025]: CNN used during training to identify when promoted action is complete; [0046]: weighted combination of intent from neural activity decoding and gaze tracking can be combined to determine intent; [0048]).
In re claim 14, regarding the limitations, “wherein the cortical interface device is a first cortical interface device implanted at a first region of the motor cortex, the system further comprising: a second cortical interface device to be surgically implanted at a second region of the motor cortex of the patient”, see in re claim 3 above.
In re claim 15, regarding the limitations, “wherein the action comprises squeezing a hand or throwing an object”, see in re claim 5 above.
In re claim 16, regarding the limitations, “wherein the action is associated with a binary response”, see in re claim 6 above.
Claim 4 is rejected under 35 U.S.C. 103 as being unpatentable over Colachis et al. US 2023/0062326) in view of NPL “Cognitive motor dissociation to predict time to functional recovery in patients with acute brain injury” (hereinafter referred to as “Egbebike”) in view of Alcaide et al. (US 2020/0192478) in view of Patak et al. (US 2015/0213214) in view of Mercanzini et al. (US 2012/0277834).
In re claim 4, the proposed combination fails to yield further comprising: removing the cortical interface device within thirty days of placement.
Mercanzini teaches an analogous cortical interface device [0005], and teaches further comprising: removing the cortical interface device within thirty days of placement [0006].
Mercanzini further teaches that the cortical electrode array may be removed when it is no longer required [0006], specifically when it is used as a diagnostic tool for recording and stimulation [0006].
It would have been obvious to someone of ordinary skill in the art at the time the instant invention was filed to modify the method for communicating with a patient that is clinically unresponsive yielded by the proposed combination, to provide removing the cortical interface device within thirty days of placement, as taught by Mercanzini, because the cortical interface device may be removed when it is no longer required, specifically when it is used as a diagnostic tool for recording and stimulation.
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.
Contact
Any inquiry concerning this communication or earlier communications from the examiner should be directed to RUMAISA R BAIG whose telephone number is (571)270-0175. The examiner can normally be reached Mon-Fri: 8am- 5pm.
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, David Hamaoui can be reached at (571) 270-5625. 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.
/RUMAISA RASHID BAIG/Examiner, Art Unit 3796
/DAVID HAMAOUI/SPE, Art Unit 3796
Prosecution Insights