DETAILED ACTION
Applicant' s arguments, filed 12/24/2025 have been fully considered. The following rejections and/or objections are either reiterated or newly applied. They constitute the complete set presently being applied to the instant application.
Applicants have amended their claims, filed 09/09/2022, and therefore rejections newly made in the instant office action have been necessitated by amendment.
Claims 1-3, 5, 9-18, and 20-22 are the current claims hereby under examination.
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Objections
Claims 5, 14, and 22 are objected to because of the following informalities:
Claim 5 it appears that “a first frequency band of the EEG signals” and “a second frequency band of the EEG signals” should read “a first frequency band, of the multiple frequency bands, of the EEG signals” and “a second frequency band, of the multiple frequency bands, of the EEG signals” to more clearly indicate that the first and second frequency bands are a subset of the multiple frequency bands in claim 1.
Claim 14 lines 4-5 it appears that “data for each data file” should read “the data for each data file”
Claim 22 lines 2 and 4 it appears that “for each for” should read “for each of”
Claim 22 lines 4-5 it appears that “a time at which the carotid artery of the patient was clamped” should read “the time at which the carotid artery of the patient was clamped”
Appropriate correction is required.
Claim Rejections - 35 USC § 112(b)
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.
Claim 22 is 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.
Claim 22 recites “first EEG signals” and “second EEG signals” but it is unclear if these signals are the same as, related to, a subset of, or different from “sequences of EEG signals” used to train the machine learning model of claim 1 line 10. For the purposes of this examination, the first and second EEG signals are interpreted as being a subset of the sequences of EEG signals.
Claim 22 recites “training the machine learning model using …” but it is unclear if this limitation is meant to indicate that the first and second EEG signals are used in addition to, in place of, or replacing a subset of “historical patient data …” of claim 1. For the purposes of this examination, the limitation will be interpreted as being used in addition to and/or further defining the data recited in claim 1.
Claim Rejections - 35 USC § 112(a)
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.
Claims 1, 16, and 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 claim(s) 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 inventor(s), at the time the application was filed, had possession of the claimed invention.
Claim 1 recites “a trained machine learning model that has been trained to detect reduced blood flow conditions in brains of patients, …; receiving as a machine learning output of the trained machine learning model, an indication of whether the patient has the reduced blood flow condition” However the specification does not disclose how the machine learning algorithm processes the recited input data to obtain the recited output data. The machine learning algorithm is described in functional language as a ”black box” algorithm which takes the recited inputs and transforms them into the recited outputs through an unknown processing method. In particular, paragraphs 0004-0006, 0012, 0020, and 0089-0090 describe the algorithm in functional language with mere statements of functionality. Paragraphs 0009, 0015, 0031-0033, 0041, 0062, and 0080 provide generic statements that the algorithm is trained using past data to produce the trained algorithm. Paragraphs 0042 and 0065 recite that the algorithm performs the recited transformation through pattern recognition but does not describe what types of patterns are being recognized. Overall, the specification does not appear to describe how the input features are transformed into the output indication of reduced blood flow. This rejection is further applied to the similar recitations in claims 16 and 20.
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 1-3, 5, 9-18, and 20-22 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more. Claims 1-3, 5, 9-18, and 20-22 are directed to a method of processing EEG signals using a computational algorithm, which is an abstract idea. Claims 1-3, 5, 9-18, and 20-22 do not include additional elements that integrate the exception into a practical application or that are sufficient to amount to significantly more than the judicial exception for the reasons provided below which are in line with the 2014 Interim Guidance on Patent Subject Matter Eligibility (Federal Register, Vol. 79, No. 241, p 74618, December 16, 2014), the July 2015 Update on Subject Matter Eligibility (Federal Register, Vol. 80, No. 146, p. 45429, July 30, 2015), the May 2016 Subject Matter Eligibility Update (Federal Register, Vol. 81, No. 88, p. 27381, May 6, 2016), and the 2019 Revised Patent Subject Matter Eligibility Guidance (Federal Register, Vol. 84, No. 4, page 50, January 7, 2019).
The analysis of claim 1 is as follows:
Step 1: Claim 1 is drawn to a process.
Step 2A – Prong One: Claim 1 recites an abstract idea. In particular, claim 1 recites the following limitations:
[A1] generating, using the EEG signals, a set of feature values for features of the patient
[B1] providing the feature values as input to detect reduced blood flow conditions of patients
[C1] receiving an indication of whether the patient has the reduced blood flow condition
[D1] providing the indication of whether the patient has the reduced blood flow condition
These elements [A1]-[D1] of claim 1 are drawn to an abstract idea since they involve a mental process that can be practically performed in the human mind including observation, evaluation, judgment, and opinion and using pen and paper.
Step 2A – Prong Two: Claim 1 recites the following limitations that are beyond the judicial exception:
[A2] receiving patient data comprising a set of electroencephalography (EEG) signals generated by an EEG device measuring brain function of the patient
[B2] a trained machine learning model that has been trained
[C2] the trained machine learning model is trained based on historical patient data for a plurality of patients, the historical data for each individual patient in the plurality of patients comprising sequences of EEG signals for the individual patient that were monitored during a medical procedure being performed on the individual patient, one or more medical professional notes generated by a medical professional during the medical procedure, and annotations indicating when, relative to the sequences of EEG signals, a reduced blood flow condition was detected for the individual patient during the medical procedure, wherein the medical professional notes indicate when, during the medical procedure, a carotid artery of the patient was clamped
[D2] a device for presentation
These elements [A2]-[D2] of claim 1 do not integrate the exception into a practical application of the exception. In particular, the element [A2] is merely adding insignificant extra-solution activity to the judicial exception, i.e., mere data gathering at a higher level of generality - see MPEP 2106.04(d) and MPEP 2106.05(g). Furthermore, the elements [B2] and [D2] are merely an instruction to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea - see MPEP 2106.04(d) and MPEP 2106.05(f). Additionally, the elements [B2]-[C2] are nothing more than the computer implementation/automation of an abstract mental process of screening a patient are recitations drawn to training such a computer implimentation, which is what a physician is trained for and typically does with a patient in a diagnostic setting
Step 2B: Claim 1 does not recite additional elements that amount to significantly more than the judicial exception itself. In particular, the recitation “receiving patient data comprising a set of electroencephalography (EEG) signals generated by an EEG device measuring brain function of the patient” does not qualify as significantly more because this limitation merely describes the nature of the received data and does not incorporate the EEG device as part of the claimed invention. Also, the recitation “receiving patient data comprising a set of electroencephalography (EEG) signals generated by an EEG device measuring brain function of the patient” is merely insignificant extrasolution activity to the judicial exception, e.g., mere data gathering in conjunction with the abstract idea that uses conventional, routine, and well known elements or simply displaying the results of the algorithm that uses conventional, routine, and well known elements. In particular, the data acquirer is nothing more than an EEG electrode. Such EEG sensors are conventional as evidenced by:
U.S. Patent Application Publication No. US 2006/0173510 A1 (Besio) discloses that EEG electrodes are conventional (paragraph 0013 of Besio);
U.S. Patent No. US 3993046 A (Fernandez) discloses that EEG signals are conventionally derived from electrodes (Col 1 lines 31-56 of Fernandez);
U.S. Patent No. US 3859988 A (Lencioni) discloses that EEG electrodes are conventional (Col 2 lines 35-49 of Lencioni); and
U.S. Patent Application Publication No. US 2015/0313498 A1 (Coleman) discloses that EEG electrodes and EEG electrode caps in various configurations are conventional (paragraphs 0108 of Coleman).
Further, the elements [B2]-[D2] do not qualify as significantly more because this limitation is simply an instruction to implement the abstract idea onto a computing device and use the computing device to replace the human mind. This element does not qualify as significantly more because the implementation onto a computer that this limitation requires is simply appending well-understood, routine and conventional activities previously known in the industry, specified at a high level of generality, to the judicial exception, e.g., a claim to an abstract idea requiring no more than a generic computer to perform generic computer functions that are well-understood, routine and conventional activities previously known in the industry (see Electric Power Group, 830 F.3d 1350 (Fed. Cir. 2016); Alice Corp. v. CLS Bank Int’l, 110 USPQ2d 1976 (2014)) and/or a claim to an abstract idea requiring no more than being stored on a computer readable medium which is a well-understood, routine and conventional activity previously known in the industry (see Electric Power Group, 830 F.3d 1350 (Fed. Cir. 2016); Alice Corp. v. CLS Bank Int’l, 110 USPQ2d 1976 (2014); SAP Am. v. InvestPic, 890 F.3d 1016 (Fed. Circ. 2018)). Additionally the steps of training are recited at a high degree of generality and do not preclude a human mind being trained in a similar manner (i.e. a person may be presented with annotated data and learn to distinguish particular patterns indicating particular conditions) the recited training and or pattern detection are not described in such a way as to preclude the training and function of the machine learning algorithm being performed in the human mind. Additionally, claiming the improved speed or efficiency inherent with applying the abstract idea on a computer does not integrate a judicial exception into a practical application or provide an inventive concept. Intellectual Ventures | LLC v. Capital One Bank (USA), 792 F.3d 1363, 1367, 115 USPQ2d 1636, 1639 (Fed. Cir. 2015). MPEP 2106.05(f)(2)
In view of the above, the additional elements individually do not integrate the exception into a practical application and do not amount to significantly more than the above-judicial exception (the abstract idea). Looking at the limitations as an ordered combination (that is, as a whole) adds nothing that is not already present when looking at the elements taking individually. There is no indication that the combination of elements improves the functioning of a computer, for example, or improves any other technology. There is no indication that the combination of elements permits automation of specific tasks that previously could not be automated. There is no indication that the combination of elements includes a particular solution to a computer-based problem or a particular way to achieve a desired computer-based outcome. Rather, the collective functions of the claimed invention merely provide conventional computer implementation, i.e., the computer is simply a tool to perform the process.
Claims 2-3, 5, 9-15, and 21-22 depend from claim 1, and recite the same abstract idea as claim 1. Furthermore, these claims only contain recitations that further limit the abstract idea (that is, the claims only recite limitations that further limit the algorithm).
In view of the above, the additional elements individually do not integrate the exception into a practical application and do not amount to significantly more than the above-judicial exception (the abstract idea). Looking at the limitations of each claim as an ordered combination in conjunction with the claims from which they depend (that is, as a whole) adds nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer, for example, or improves any other technology. There is no indication that the combination of elements permits automation of specific tasks that previously could not be automated. There is no indication that the combination of elements includes a particular solution to a computer-based problem or a particular way to achieve a desired computer-based outcome. Rather, the collective functions of the claimed invention merely provide conventional computer implementation, i.e., the computer is simply a tool to perform the process.
Claims 16 and 20 recite the same abstract idea as claim 1 and are rejected on the same basis as claim 1.
Claim 16 and 20 recite the following additional limitations not already addressed in the above rejection of claim 1:
Step 2A – Prong Two: Claims 16 and 20 recite the following limitations that are beyond the judicial exception:
[A2] one or more computers
[B2] one or more computer memory devices interoperably coupled with the one or more computers and having tangible, non-transitory, machine-readable media storing one or more instructions
[C2] a computer system
These elements [A2]-[C2] of claims 16-20 do not integrate the exception into a practical application of the exception. In particular, the elements [A2]-[C2] are merely an instruction to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea - see MPEP 2106.04(d) and MPEP 2106.05(f).
Further, the elements [A2]-[C2] do not qualify as significantly more because these limitations are simply appending well-understood, routine and conventional activities previously known in the industry, specified at a high level of generality, to the judicial exception, e.g., a claim to an abstract idea requiring no more than a generic computer to perform generic computer functions that are well-understood, routine and conventional activities previously known in the industry (see Electric Power Group, 830 F.3d 1350 (Fed. Cir. 2016); Alice Corp. v. CLS Bank Int’l, 110 USPQ2d 1976 (2014)) and/or a claim to an abstract idea requiring no more than being stored on a computer readable medium which is a well-understood, routine and conventional activity previously known in the industry (see Electric Power Group, 830 F.3d 1350 (Fed. Cir. 2016); Alice Corp. v. CLS Bank Int’l, 110 USPQ2d 1976 (2014); SAP Am. v. InvestPic, 890 F.3d 1016 (Fed. Circ. 2018)).
In view of the above, the additional elements individually do not integrate the exception into a practical application and do not amount to significantly more than the above-judicial exception (the abstract idea). Looking at the limitations as an ordered combination (that is, as a whole) adds nothing that is not already present when looking at the elements taking individually. There is no indication that the combination of elements improves the functioning of a computer, for example, or improves any other technology. There is no indication that the combination of elements permits automation of specific tasks that previously could not be automated. There is no indication that the combination of elements includes a particular solution to a computer-based problem or a particular way to achieve a desired computer-based outcome. Rather, the collective functions of the claimed invention merely provide conventional computer implementation, i.e., the computer is simply a tool to perform the process.
Claims 17-18 depend from claim 16, and recite the same abstract idea as claim 16. Furthermore, these claims only contain recitations that further limit the abstract idea (that is, the claims only recite limitations that further limit the algorithm).
In view of the above, the additional elements individually do not integrate the exception into a practical application and do not amount to significantly more than the above-judicial exception (the abstract idea). Looking at the limitations of each claim as an ordered combination in conjunction with the claims from which they depend (that is, as a whole) adds nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer, for example, or improves any other technology. There is no indication that the combination of elements permits automation of specific tasks that previously could not be automated. There is no indication that the combination of elements includes a particular solution to a computer-based problem or a particular way to achieve a desired computer-based outcome. Rather, the collective functions of the claimed invention merely provide conventional computer implementation, i.e., the computer is simply a tool to perform the process.
Claim Rejections - 35 USC § 103
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.
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.
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.
Claims 1-3, 5, 9-11, 16-18, 20, and 22 are rejected under 35 U.S.C. 103 as being unpatentable over Tzvieli US Patent Number US 10638938 B1 hereinafter Tzvieli in view of Shin US Patent Application Publication Number US 2020/0229723 A1 hereinafter Shin and further in view of Barrett US Patent Number US 6615065 B1 hereinafter Barrett.
Regarding claim 1, Tzvieli discloses a method performed by one or more data processing apparatus (Abstract: a computer), the method comprising:
receiving patient data comprising a set of electroencephalography (EEG) signals generated by an EEG device measuring brain function of the patient (Col 48 lines 54-58: EEG electrodes positioned on the user’s head; Col 46 lines 6-28: the EEG signals are used by the machine learning model and are thus received);
generating, using the EEG signals, a set of feature values for features of the patient (Col 27 line 45 – Col 28 line 15: various types of feature values may be used, EEG may be one of the data types used to generate the feature values);
providing the feature values as input to a trained machine learning model that has been trained to detect reduced blood flow conditions in brains of patients (Col 46 lines 6-28: the EEG values are provided to a trained machine learning model; Col 41 lines 26-37: the model may be trained to detect a stroke, a type of reduced blood flow condition) wherein the trained machine learning model is trained based on historical patient data for a plurality of patients (Col 28 line 56 – Col 29 line 32: the model may be trained as a general model using data form a plurality of users), the historical data for each individual patient in the plurality of patients comprising sequences of EEG signals for the individual patient that were monitored during a medical procedure being performed on the individual patient, one or more medical professional notes generated by a medical professional during the medical procedure, and annotations indicating when, relative to the sequences of EEG signals, a reduced blood flow condition was detected for the individual patient during the medical procedure (Col 27 lines 16-60: the training data during a certain period of time includes labels which may include annotations by experts involving when the physiological response occurred and to what extent it occurred; Col 46 lines 6-28: the data may be EEG data. Thus, Tzvieli at least suggests medical professionals annotating EEG data during a medical procedure to denote periods when reduced blood flow conditions occur),
receiving, as a machine learning output of the trained machine learning model, an indication of whether the patient has the reduced blood flow condition (Col 44 lines 9-30: outputting a value indicative of atypical blood flow patterns; Col 49 lines 19-46: the model outputs a value indicative of a risk that the user has suffered from a stroke); and
providing the indication of whether the patient has the reduced blood flow condition to a device for presentation to a person (Col 30 lines 11-27: the display presents the physiological response or alert if the physiological response surpasses a threshold).
Tzvieli fails to further disclose or reasonably suggest the method wherein the feature values comprise EEG power values for multiple frequency bands, and wherein the medical professional notes indicate when, during the medical procedure, a carotid artery of the patient was clamped.
Shin teaches an apparatus for measuring brain cell activity in artificial blood circulation according to an embodiment of the present invention may include a measuring unit that measures EEG signals; an analog-to-digital converter (ADC) that converts the EEG signals measured at the measuring unit into digital signals; a control unit that calculates EEG parameters from the digital EEG signals converted at the ADC, and calculates end-tidal carbon dioxide tension and cerebral blood flow from the EEG parameters (Abstract). Thus, Shin falls within the same field of endeavor as Applicant’s invention.
Shin teaches that power ratios between multiple frequency bands and/or total power may be used to determine cerebral blood flow (Paragraphs 0035).
It would have been obvious to one of ordinary skill in the art prior to the effective filling date of the invention to utilize the power ratios of Shin as the features of Tzvieli because Shin teaches that the power ratios are suitable for determining cerebral blood flow and thus utilizing them as the features of Tzvieli is a simple substitution of one known element for another with no surprising technical effect.
Tzvieli fails to further disclose or reasonably suggest the method wherein the medical professional notes indicate when, during the medical procedure, a carotid artery of the patient was clamped.
Barrett teaches a method and apparatus for spectrophotometric in vivo monitoring of blood metabolites such as hemoglobin oxygen concentration at a plurality of different areas or regions on the same organ or test site on an ongoing basis, by applying a plurality of spectrophotometric sensors to a test subject at each of a corresponding plurality of testing sites and coupling each such sensor to a control and processing station, operating each of said sensors to spectrophotometrically irradiate a particular region within the test subject; detecting and receiving the light energy resulting from said spectrophotometric irradiation for each such region and conveying corresponding signals to said control and processing station, analyzing said conveyed signals to determine preselected blood metabolite data, and visually displaying the data so determined for each of a plurality of said areas or regions in a comparative manner (Abstract). Thus, Barrett is reasonably pertinent to the problem at hand.
Barrett teaches that application of an arterial clamp to a carotid artery during surgery reduces blood flow to the brain and that it is desirable to note the time of application of the clamp and the time at which the clamp was removed as these times represent the time at which blood flow to the brain is reduced and restored (Col 7 lines 13-42).
It would have been obvious to one of ordinary skill in the art prior to the effective filling date of the invention to modify the method of Tzvieli in view of Shin such that the annotated EEG training data of Tzvieli (Col 27 lines 16-60; Col 46 lines 6-28) includes annotations denoting when an arterial clamp was applied and removed as Barrett teaches that these times represent start and end times to a reduced blood flow condition. Such precise labelling of a known event would be useful for training a machine algorithm configured for detecting reduced blood flow events such as ischemia or stroke (Tzvieli: Col 44 lines 9-30; Col 49 lines 19-46)
Regarding claim 16, Tzvieli discloses a computer-implemented system (Abstract: a computer), comprising:
one or more computers (Abstract: a computer); and
one or more computer memory devices interoperably coupled with the one or more computers and having tangible, non-transitory, machine-readable media storing one or more instructions that, when executed by the one or more computers, perform operations (Col 19 lines 38-47; Col 29 lines 33-49: the system comprises a memory or a plurality of memories associated with a computer network for distributing the model) comprising:
receiving patient data comprising a set of electroencephalography (EEG) signals generated by an EEG device measuring brain function of the patient (Col 48 lines 54-58: EEG electrodes positioned on the user’s head; Col 46 lines 6-28: the EEG signals are used by the machine learning model and are thus received);
generating, using the EEG signals, a set of feature values for features of the patient (Col 27 line 45 – Col 28 line 15: various types of feature values may be used, EEG may be one of the data types used to generate the feature values);
providing the feature values as input to a trained machine learning model that has been trained to detect reduced blood flow conditions in brains of patients (Col 46 lines 6-28: the EEG values are provided to a trained machine learning model; Col 41 lines 26-37: the model may be trained to detect a stroke, a type of reduced blood flow condition); wherein the trained machine learning model is trained based on historical patient data for a plurality of patients (Col 28 line 56 – Col 29 line 32: the model may be trained as a general model using data form a plurality of users), the historical data for each individual patient in the plurality of patients comprising sequences of EEG signals for the individual patient that were monitored during a medical procedure being performed on the individual patient, one or more medical professional notes generated by a medical professional during the medical procedure, and annotations indicating when, relative to the sequences of EEG signals, a reduced blood flow condition was detected for the individual patient during the medical procedure (Col 27 lines 16-60: the training data during a certain period of time includes labels which may include annotations by experts involving when the physiological response occurred and to what extent it occurred; Col 46 lines 6-28: the data may be EEG data. Thus, Tzvieli at least suggests medical professionals annotating EEG data during a medical procedure to denote periods when reduced blood flow conditions occur),
receiving, as a machine learning output of the trained machine learning model, an indication of whether the patient has the reduced blood flow condition (Col 44 lines 9-30: outputting a value indicative of atypical blood flow patterns; Col 49 lines 19-46: the model outputs a value indicative of a risk that the user has suffered from a stroke); and
providing the indication of whether the patient has the reduced blood flow condition to a device for presentation to a person (Col 30 lines 11-27: the display presents the physiological response or alert if the physiological response surpasses a threshold).
Tzvieli fails to further disclose or reasonably suggest the system wherein the feature values comprise EEG power values for multiple frequency bands, and wherein the medical professional notes indicate when, during the medical procedure, a carotid artery of the patient was clamped.
Shin teaches that power ratios between multiple frequency bands and/or total power may be used to determine cerebral blood flow (Paragraphs 0035).
It would have been obvious to one of ordinary skill in the art prior to the effective filling date of the invention to utilize the power ratios of Shin as the features of Tzvieli because Shin teaches that the power ratios are suitable for determining cerebral blood flow and thus utilizing them as the features of Tzvieli is a simple substitution of one known element for another with no surprising technical effect.
Tzvieli fails to further disclose or reasonably suggest the system wherein the medical professional notes indicate when, during the medical procedure, a carotid artery of the patient was clamped.
Barrett teaches that application of an arterial clamp to a carotid artery during surgery reduces blood flow to the brain and that it is desirable to note the time of application of the clamp and the time at which the clamp was removed as these times represent the time at which blood flow to the brain is reduced and restored (Col 7 lines 13-42).
It would have been obvious to one of ordinary skill in the art prior to the effective filling date of the invention to modify the system of Tzvieli in view of Shin such that the annotated EEG training data of Tzvieli (Col 27 lines 16-60; Col 46 lines 6-28) includes annotations denoting when an arterial clamp was applied and removed as Barrett teaches that these times represent start and end times to a reduced blood flow condition. Such precise labelling of a known event would be useful for training a machine algorithm configured for detecting reduced blood flow events such as ischemia or stroke (Tzvieli: Col 44 lines 9-30; Col 49 lines 19-46)
Regarding claim 20, Tzvieli discloses a non-transitory, computer-readable medium storing one or more instructions executable by a computer system (Abstract: a computer executing the method) to perform operations comprising:
receiving patient data comprising a set of electroencephalography (EEG) signals generated by an EEG device measuring brain function of the patient (Col 48 lines 54-58: EEG electrodes positioned on the user’s head; Col 46 lines 6-28: the EEG signals are used by the machine learning model and are thus received);
generating, using the EEG signals, a set of feature values for features of the patient (Col 27 line 45 – Col 28 line 15: various types of feature values may be used, EEG may be one of the data types used to generate the feature values);
providing the feature values as input to a trained machine learning model that has been trained to detect reduced blood flow conditions in brains of patients (Col 46 lines 6-28: the EEG values are provided to a trained machine learning model; Col 41 lines 26-37: the model may be trained to detect a stroke, a type of reduced blood flow condition), wherein the trained machine learning model is trained based on historical patient data for a plurality of patients (Col 28 line 56 – Col 29 line 32: the model may be trained as a general model using data form a plurality of users), the historical data for each individual patient in the plurality of patients comprising sequences of EEG signals for the individual patient that were monitored during a medical procedure being performed on the individual patient, one or more medical professional notes generated by a medical professional during the medical procedure, and annotations indicating when, relative to the sequences of EEG signals, a reduced blood flow condition was detected for the individual patient during the medical procedure (Col 27 lines 16-60: the training data during a certain period of time includes labels which may include annotations by experts involving when the physiological response occurred and to what extent it occurred; Col 46 lines 6-28: the data may be EEG data. Thus, Tzvieli at least suggests medical professionals annotating EEG data during a medical procedure to denote periods when reduced blood flow conditions occur),
receiving, as a machine learning output of the trained machine learning model, an indication of whether the patient has the reduced blood flow condition (Col 44 lines 9-30: outputting a value indicative of atypical blood flow patterns; Col 49 lines 19-46: the model outputs a value indicative of a risk that the user has suffered from a stroke); and
providing the indication of whether the patient has the reduced blood flow condition to a device for presentation to a person (Col 30 lines 11-27: the display presents the physiological response or alert if the physiological response surpasses a threshold).
Tzvieli fails to further disclose or reasonably suggest the system wherein the feature values comprise EEG power values for multiple frequency bands, and wherein the medical professional notes indicate when, during the medical procedure, a carotid artery of the patient was clamped.
Shin teaches that power ratios between multiple frequency bands and/or total power may be used to determine cerebral blood flow (Paragraphs 0035).
It would have been obvious to one of ordinary skill in the art prior to the effective filling date of the invention to utilize the power ratios of Shin as the features of Tzvieli because Shin teaches that the power ratios are suitable for determining cerebral blood flow and thus utilizing them as the features of Tzvieli is a simple substitution of one known element for another with no surprising technical effect.
Tzvieli fails to further disclose or reasonably suggest the system wherein the medical professional notes indicate when, during the medical procedure, a carotid artery of the patient was clamped.
Barrett teaches that application of an arterial clamp to a carotid artery during surgery reduces blood flow to the brain and that it is desirable to note the time of application of the clamp and the time at which the clamp was removed as these times represent the time at which blood flow to the brain is reduced and restored (Col 7 lines 13-42).
It would have been obvious to one of ordinary skill in the art prior to the effective filling date of the invention to modify the system of Tzvieli in view of Shin such that the annotated EEG training data of Tzvieli (Col 27 lines 16-60; Col 46 lines 6-28) includes annotations denoting when an arterial clamp was applied and removed as Barrett teaches that these times represent start and end times to a reduced blood flow condition. Such precise labelling of a known event would be useful for training a machine algorithm configured for detecting reduced blood flow events such as ischemia or stroke (Tzvieli: Col 44 lines 9-30; Col 49 lines 19-46)
Regarding claims 2 and 17, Tzvieli in view of Shin further in view of Barrett teaches the method and system of claims 1 and 16 respectively. Modified Tzvieli further discloses the method and system wherein the reduced blood flow condition comprises one of ischemia or a stroke (Col 49 lines 19-46: the model outputs a value indicative of a risk that the user has suffered from a stroke).
Regarding claims 3 and 18, Tzvieli in view of Shin further in view of Barrett teaches the method and system of claims 1 and 16 respectively. Modified Tzvieli further discloses the method and system comprising determining that the patient has the reduced blood flow condition based on the machine learning output (Col 49 lines 19-46: determining when the risk value reaches a threshold), wherein providing the indication of whether the patient has the reduced blood flow condition comprises sending an alert to one or more medical professionals (Col 30 lines 11-27: the display presents the physiological response or alert if the physiological response surpasses a threshold).
Regarding claim 5, Tzvieli in view of Shin further in view of Barrett teaches the method of claim 1. Modified Tzvieli fails to further disclose the method wherein the feature values comprise a set of ratios between power values of a first frequency band of the EEG signals and corresponding power values of a second frequency band of the EEG signals.
Shin teaches that power ratios between frequency bands and/or total power may be used to determine cerebral blood flow (Paragraph 0035).
It would have been obvious to one of ordinary skill in the art prior to the effective filling date of the invention to utilize the power ratios of Shin as the features of Tzvieli because Shin teaches that the power ratios are suitable for determining cerebral blood flow and thus utilizing them as the features of Tzvieli is a simple substitution of one known element for another with no surprising technical effect.
Regarding claims 9-11, Tzvieli in view of Shin further in view of Barrett teaches the method of claim 1. Modified Tzvieli fails to explicitly disclose the method wherein generating the feature values comprises generating a set of feature values in real-time for each second of EEG signals received from the EEG device connected to the patient. The method wherein each set of feature values comprises feature values for a time period beginning a specified amount of time before the second for which the set of feature values is generated, and the method wherein the specified amount of time is 20 seconds.
Tzvieli discloses that the model may process data in certain time windows of varying length depending on the physiological response, or condition, being monitored for. The analysis may include receiving a stream of data while the user is wearing the sensors and periodically evaluating measurements within a sliding window of a certain size (Col 24 lines 18-32). The evaluation may be performed on a computer and by comparing a metric to a threshold to by comparing current data to reference data. The time window of data used for analysis and/or comparison depends on the type of physiological response being detected. The windows may be a variety of lengths and the analysis of data may be based on a subset of data that falls within a certain window near a given time (Col 24 line 66-Col 25 line 24). Thus Tzvieli teaches the analysis of data in real time (Col 24 lines 18-32: receiving a stream of data while the user wears the sensors) which includes the generating of EEG features as described in the above rejection of claim 1 (Col 27 line 45 – Col 28 line 15: various types of feature values may be used; EEG may be one of the data types used to generate the feature values) and the analysis of said data according to specific time windows. Tzvieli further contemplates that the duration of the time windows and rate at which the analysis occurs are subject to routine optimization and experimentation according to the physiological response that is being monitored (Col 24 lines 18-32; Col 24 line 66-Col 25 line 24). Thus, the particular the window duration and period for analysis while receiving real-time data of Tzvieli is subject to routine optimization and experimentation based on the physiologic condition being monitored for as taught by Tzvieli as well as for other factors such as the type of signal being analyzed, computational constraints, and desired degree of precision and/or accuracy. Thus the limitations of claims 9-11 regarding a specific window duration and frequency of analysis are considered to be obvious in view of Tzvieli and lacking a specific surprising technical effect of the claimed window duration and analysis frequency.
Regarding claim 22, Tzvieli in view of Shin further in view of Barrett teaches the method of claim 1. Modified Tzvieli further discloses the method wherein the trained machine learning model is trained by extracting, for each individual patient, (i) first EEG signals for each for a first time period preceding a time at which the physiological response occurred and (ii) second EEG signals for each for a second time period following a time at which the physiological response occurred; and training the trained machine learning model using the first EEG signals and the second EEG signals for each individual patient (Col 27 lines 16-60: the training data during a certain period of time includes labels which may include annotations by experts involving when the physiological response occurred, to what extent it occurred, and/or how long it occurred; Col 46 lines 6-28: the data may be EEG data; Col 28 line 56 – Col 29 line 32: the model may be a personalized model which is trained using individual data).
Modified Tzvieli fails to further disclose the physiological response being the carotid artery of the patient was clamped.
Barrett teaches that application of an arterial clamp to a carotid artery during surgery reduces blood flow to the brain and that it is desirable to note the time of application of the clamp and the time at which the clamp was removed as these times represent the time at which blood flow to the brain is reduced and restored (Col 7 lines 13-42).
It would have been obvious to one of ordinary skill in the art prior to the effective filling date of the invention to modify the method of modified Tzvieli such that the annotated EEG training data of Tzvieli (Col 27 lines 16-60; Col 46 lines 6-28) includes annotations denoting when an arterial clamp was applied and removed as Barrett teaches that these times represent start and end times to a reduced blood flow condition. Such precise labelling of a known event would be useful for training a machine algorithm configured for detecting reduced blood flow events such as ischemia or stroke (Tzvieli: Col 44 lines 9-30; Col 49 lines 19-46)
Claims 12-14 are rejected under 35 U.S.C. 103 as being unpatentable over Tzvieli US Patent Number US 10638938 B1 hereinafter Tzvieli in view of Shin US Patent Application Publication Number US 2020/0229723 A1 hereinafter Shin and further in view of Barrett US Patent Number US 6615065 B1 hereinafter Barrett as applied to claim 1 above and further in view of Dala US Patent Application Publication Number US 2013/0097086 A1 hereinafter Dala.
Regarding claim 12, Tzvieli in view of Shin further in view of Barrett teaches the method of claim 1. Modified Tzvieli fails to further disclose the method wherein the patient data comprises a set of data files that each include different formats of data including multiple data files comprising data for the set of EEG signals.
Dala teaches a system for securing patient medical information for communication over a potentially vulnerable system includes separating patient's medical file into a demographics layer and a data layer, separately encrypting the demographic layer and data layer using different encryption keys, and providing servers in a communication and processing system with a decryption key for the layer processed by such server. Medical file data may be separated into more than two layers. Users accessing the system are authenticated using standard techniques. By separately encrypting different parts of a patient medical record, processing and communication of patient medical files by intermediary servers is enabled without risking disclosure of sensitive patient information if such servers are compromised (Abstract). Thus Dala is reasonably pertinent to the problem at hand.
Dala teaches that patient data files may include a variety of data types with different formats including formats for EEG data. The different data formats may be a result of data being supplied from different vendors (Paragraphs 0099, 0112-0113, 0161, and 0189)
It would have been obvious to one of ordinary skill in the art prior to the effective filling date of the invention to incorporate the patient file having multiple different data types as taught by Dala into the method of modified Tzvieli because Tzvieli discloses that the patient data may include the samples, feature values, and labels (Tzvieli: Col 27 lines 16-44) and each of these information types may better lend itself to a particular file type and/or format.
Regarding claim 13, Tzvieli in view of Dala teaches the method of claim 12. Modified Tzvieli fails to further disclose the method comprising preprocessing the data of each data file to convert the data of each data file to a same standard format.
Dala teaches that a data format and communication protocol translator module may be implemented to convert data files and communication protocols to a common format (Paragraphs 0112-0113).
It would have been obvious to one of ordinary skill in the art prior to the effective filling date of the invention to incorporate the data format and communication protocol translator module of Dala into the method of modified Tzvieli because the translator module would allow the method of Tzvieli to operate even when using different data types such as from different vendors and may improve computational efficiency by converting all of the data to a common type.
Regarding claim 14, Tzvieli in view of Shin in view of Barrett further in view of Dala teaches the method of claim 13. Modified Tzvieli further discloses the method comprising: maintaining each data file in an open state throughout a time period in which the patient is being monitored (Col 24 line 18-32: receiving a stream of data and periodically evaluating the measurements. Thus the file into which data is being streamed remains “open” for the period of time in which data is being gathered).
Modified Tzvieli fails to further disclose the method wherein: for each data file, continuously or periodically scanning memory locations at which data for each data file is stored to acquire any new data written to the memory locations.
Dala teaches a system wherein new data is uploaded to a server which updates a polling response section. A handheld device can then query the server and the polling response section responds to the query if new data is available. The handheld device can then download the new data for processing (Paragraph 0128).
It would have been obvious to one of ordinary skill in the art prior to the effective filling date of the invention to incorporate the new data querying of Dala into the method of modified Tzvieli because such a configuration would allow the processing of current signals to be performed remotely and in near-real time while not requiring a continuous communication channel since new packets of data can be sent to the server and downloaded by a separate processing device at regular intervals. Such a configuration may reduce the network bandwidth requirements for remote processing while implementing only a small delay in data processing.
Claim 15 is rejected under 35 U.S.C. 103 as being unpatentable over Tzvieli US Patent Number US 10638938 B1 hereinafter Tzvieli in view of Shin US Patent Application Publication Number US 2020/0229723 A1 hereinafter Shin and in view of Barrett US Patent Number US 6615065 B1 hereinafter Barrett further in view of Dala US Patent Application Publication Number US 2013/0097086 A1 hereinafter Dala as applied to claim 14 above and further in view of Panasonic the Machine English Translation of Japanese Patent Application Publication Number JPH08286967A hereinafter Panasonic.
Regarding claim 15, Tzvieli in view of Dala teaches the method of claim 14. Modified Tzvieli fails to further disclose the method wherein continuously or periodically scanning memory locations at which data for each data file is stored to acquire any new data written to the memory locations comprises monitoring a flag that indicates an end of file location in memory for the data file.
Panasonic teaches a system and method to allow for the monitoring of past information while continuing to record new information such that all past and present information may be monitored (Abstract). Thus, Panasonic is reasonably pertinent to the problem at hand.
Panasonic teaches that a flag may be used to denote the end point of an address space and is used to denote new unread data from old, previously read data. The flag may prevent the device from writing in locations where data that has not yet ben read is present (Page 2 paragraphs 4-5).
It would have been obvious to one of ordinary skill in the art prior to the effective filling date of the invention to implement the flags at the end of data addresses as taught by Panasonic into the method of modified Tzvieli because Panasonic teaches that these flags can be used to denote areas with new, unread data to prevent it from being overwritten. The flags may further serve to denote which parts of data stored on a server have yet to be transmitted for processing or “read”.
Claim 21 is rejected under 35 U.S.C. 103 as being unpatentable over Tzvieli US Patent Number US 10638938 B1 hereinafter Tzvieli in view of Shin US Patent Application Publication Number US 2020/0229723 A1 hereinafter Shin and further in view of Barrett US Patent Number US 6615065 B1 hereinafter Barrett as applied to claim 1 above and further in view of Grudic US Patent Application Publication Number US 2016/0162786 A1 hereinafter Grudic
Regarding claim 21, Tzvieli in view of Shin further in view of Barrett teaches the method of claim 1. Modified Tzvieli fails to explicitly disclose the method wherein the trained machine learning model is trained to identify, from a plurality of EEG-derived features, the features corresponding to the set of feature values as being indicative of the reduced blood flow condition, wherein the features corresponding to the set of feature values are less than all of the plurality of EEG-derived features.
Grudic teaches methods and systems for autonomously building a predictive model of outcomes. A most-predictive set of signals is identified out of a set of signals for each of one or more outcomes. A set of probabilistic predictive models is autonomously learned, where a prediction of an outcome is derived from the model that uses as inputs values obtained from the set of signals. Various embodiments are also disclosed that apply predictive models to various physiological events (Abstract). Thus, Naber is reasonably pertinent to the problem at hand.
Grudic teaches a system for identifying predictive variables from a plurality of variables and generating a predictive model using only the predictive variables (Paragraphs 0049-0053). Thus, Naber teaches a system and method for selecting a subset of features that are most predictive of a given outcome from a plurality of features.
It would have been obvious to one of ordinary skill in the art prior to the effective filling date of the invention to incorporate the feature selection method of Grudic into the method of modified Tzvieli because the feature selection method of Grudic allows the system to only utilize predictive features and thus would eliminate “noise” generated by unpredictive features and would further reduce the processing requirements of the algorithm since fewer features are being analyzed.
Response to Arguments
Applicant’s arguments with respect to claims 1, 16, and 20 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
Applicant arguments with respect to the rejections previously presented under 25 USC 112a have been fully considered but are not found to be persuasive. In particular Applicant’s argument that one of ordinary skill in the art would readily understand how the various types of machine learning models would generate the output indication based on the disclosed training data is not found to be persuasive. This argument is not found to be persuasive because MPEP 2161.01 recites: It is not enough that one skilled in the art could write a program to achieve the claimed function because the specification must explain how the inventor intends to achieve the claimed function to satisfy the written description requirement. See, e.g., Vasudevan Software, Inc. v. MicroStrategy, Inc., 782 F.3d 671, 681-683, 114 USPQ2d 1349, 1356, 1357 (Fed. Cir. 2015). The specification does not describe the particular algorithm utilized to transform the recited inputs into the recited outputs. Additionally, the specification does not provide detailed description of the construction of the machine learning model or its specific training methods. The recitations of the specification to train the model using specific types of data are considered insufficient to support the claimed trained machine learning model producing the recited outputs from the recited inputs.
Regarding Applicant’s argument regarding the rejection presented under 35 USC 101. Applicant argues that the claimed invention provides improvements to computer technology and a computer functionality and that training the model on “rich” data results in more accurate detection of reduced blood flow conditions and improves how the machine learning model itself operates.
This argument is not found to be persuasive because it is not commensurate in scope with the present claim language. The present claim language only recites training a model and using said model. There are no limitations drawn towards improved accuracy over other models being trained on less “rich” data nor any indication that the labeled data used for training would be considered “rich” data as compared to other labelled data.
Applicant further argues that the claimed solution cannot be practically performed in the human mind because the claimed model evaluates features that the human mind cannot detect and is performed more rapidly than can be performed in the human mind.
These arguments are not found to be persuasive because the claim only indicates that power values of frequency bands are analyzed by the model and the human mind can readily compare provided power values for different frequency spectrums. Additionally claiming the improved speed or efficiency inherent with applying the abstract idea on a computer does not integrate a judicial exception into a practical application or provide an inventive concept. Intellectual Ventures | LLC v. Capital One Bank (USA), 792 F.3d 1363, 1367, 115 USPQ2d 1636, 1639 (Fed. Cir. 2015). MPEP 2106.05(f)(2). Finally, the features utilized and exactly how they are utilized to detect reduced blood flow conditions are not explicitly recited in the claim with a sufficient level of complexity to preclude the method from being performed in the human mind. Applicant’s arguments are not commensurate in scope with the present claim language.
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 MATTHEW ERIC OGLES whose telephone number is (571)272-7313. The examiner can normally be reached M-F 8:00AM - 5:30PM.
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, Jason Sims can be reached on Monday-Friday from 9:00AM – 4:00PM at (571) 272 – 7540. 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.
/MATTHEW ERIC OGLES/Examiner, Art Unit 3791
/JASON M SIMS/Supervisory Patent Examiner, Art Unit 3791