DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Objections
Claim 1 and 10 objected to because of the following informalities: In claim 1, the use of a period, “.” in the list of steps (or, for claim 10, the actions the processor is configured to perform) is improper. The use of parentheses after each letter (or roman numeral) is advised (i.e., “a)” “b)”, “i)”, “ii)”, etc). Appropriate correction is required. (See MPEP 608.01(m).
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.
Claim 1-20 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The 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.
Regarding claim 1, the claim recites “using a prediction model to combine at least four parameters derived from the electroencephalogram and the electrocardiogram into a final index of sepsis.” However, the written description for the index of sepsis is inadequate since the specification merely recites an intended result rather than describing how the resulting index is achieved.
Quoting from MPEP 2161.01 (I): Similarly, original claims may lack written description when the claims define the invention in functional language specifying a desired result but the specification does not sufficiently describe how the function is performed or the result is achieved. For software, this can occur when the algorithm or steps/procedure for performing the computer function are not explained at all or are not explained in sufficient detail (simply restating the function recited in the claim is not necessarily sufficient). In other words, the algorithm or steps/procedure taken to perform the function must be described with sufficient detail so that one of ordinary skill in the art would understand how the inventor intended the function to be performed. See MPEP §§ 2163.02 and 2181, subsection IV.
The recitation of “a final index of sepsis” resulting from an output in a prediction model does not have an adequate written description since the specification does not describe how the final index of sepsis is achieved, or what the index of sepsis may be. The specification describes where the index is derived from (pg. 3; para (1)), but does not describe what functions are performed by the neural network to achieve the function. The description of figure 1 (pg. 4, para. 1) recites that features are derived from the electric recording to achieve the index of sepsis, but does not disclose how this is achieved from the recording. Similarly, the description of Fig. 1 in the detailed description recites that the electrical recordings are used in combination to achieve an index, but does so with a high level of generality that does not disclose what actions are performed. The index is described as an output of the prediction model (pg. 6, para. (3)), but does not include any description on how the output is achieved from the prediction model. The use of only generic claim language and inadequate description raises questions as to how the index of sepsis is achieved, as well as what the index might be. Further, inadequate description is provided regarding the output from the prediction model, as well as the functions performed by the model to achieve the output. It is disclosed, in the steps of claim 1, calculations that are made to be input into the model. However, it is inadequately disclosed how the prediction model functions to produce the output or what the output values there are to comprise the sepsis index.
Claim 2-9 are rejected due to their dependency on claim 1.
For the same issue, claim 10 is rejected, and claims 11-20 are rejected due to their dependency from claim 10.
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.
Claims 1-20 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Regarding claim 1, the claim recites, “the level of sepsis,” “the location,” “the interbeat interval series,” “the calculation,” “the heart beat variability,” “the heart rate n-variability,” “the time domain features,” “the frequency domain features,” and “the cross-correlation and the mutual information.” The recited terms lack antecedent basis, and are therefore indefinite.
Claims 2-9 are rejected due to their dependency from claim 1.
Regarding claim 2, the claim recites, “the construction of series of the consecutive individual interbeat intervals,” “the case of heart rate variability,” “the sum,” and “the case of heart rate n-variability. The recited terms lack antecedent basis, and are therefore indefinite.
Regarding claim 3, the claim recites “the extraction,” “the energy content,” and “the energy ratios.” The recited terms lack antecedent basis, and are therefore indefinite. Additionally, the claim’s recitation of “such as” is indefinite language. It is unclear what is considered claimed subject matter.
Regarding claim 4, the claim recites “the extraction,” “the series of intervals,” “the standard deviation of the differences,” the root mean square,” “the percentage,” “the standard deviation of the intervals,” and “the standard deviation of the average intervals.” The recited terms lack antecedent basis, and are therefore indefinite. Additionally, the claim’s recitation of “such as” is indefinite language. It is unclear what is considered claimed subject matter.
Regarding claim 5, the claim recites “the extraction” and “the series.” The recited terms lack antecedent basis, and are therefore indefinite.
Regarding claim 6, the claim recites “the extraction,” “the series,” “the approximate entropy,” “the sample entropy,” “the coefficients,” and “the detrended fluctuation analysis.” The recited terms lack antecedent basis, and are therefore indefinite. Additionally, the claim’s recitation of “such as” is indefinite language. It is unclear what is considered claimed subject matter.
Regarding claim 7, the claim recites “the energy content” and “the series of intervals.” The recited terms lack antecedent basis, and are therefore indefinite.
Regarding claim 9, the claim recites “the output,” “the value of the level of sepsis,” “the value of the heart rate,” “the value of the burst suppression ratio (BSR),” “the value of the impedance,” “the value of a signal quality index,” “the value of the level of battery,” and “the trend of any value of the calculated indices.” The recited terms lack antecedent basis, and are therefore indefinite.
Further regarding claim 9, the claim recites “among others”. It is unclear what “others” is referencing. As recited, others could be referencing the locations of the output (the display and others). Or, “others” could be referencing the types of outputs listed after “the following.” Further, it is unclear what subject matter falls into the scope of “others.” The claim is therefore indefinite. “Others,” for examination purposes, is interpreted as the types of outputs on the display.
Regarding claim 10, the claim recites “the location,” the interbeat interval series,” the calculation,” “the heart rate variability,” “the heart rate n-variability,” “the time domain features,” “the frequency domain features,” and “the cross-correlation and the mutual information.” The recited terms lack antecedent basis, and are therefore indefinite.
Claims 11-20 are rejected due to their dependency from claim 10.
Regarding claim 11, the claim recites “the ear, “the subject,” and “the insular cortex.” The recited terms lack antecedent basis, and are therefore indefinite. Additionally, Claim 11 recites “step a” of claim 10, but claim 10 item a is to a sensor, not a method step. Therefore, the claim is indefinite. Lastly, claim 11 is to an apparatus, but recites a step of “recording”. A single claim which claims both an apparatus and method steps of using the apparatus is indefinite under 35 USC 112(b). See MPEP 2173.05(p).
Regarding claim 12, the claim recites “the consecutive individual interbeat intervals,” “the case of heart rate variability,” “the construction of series of intervals resulting from the sum of multiple consecutive interbeat intervals,” and “the case of heart rate n-variability.” The recited terms lack antecedent basis, and are therefore indefinite.
Regarding claim 13, the claim recites “the energy content” and “the energy ratios.” The recited terms lack antecedent basis, and are therefore indefinite. Additionally, the claim’s recitation of “such as” is indefinite language. It is unclear what is considered claimed subject matter.
Regarding claim 14, the claim recites “the energy content” and “the energy ratios.” The recited terms lack antecedent basis, and are therefore indefinite. Additionally, the claim’s recitation of “such as” is indefinite language. It is unclear what is considered claimed subject matter.
Regarding claim 15, the claim recites “the series, “the root mean square differences,” “the standard deviation of the differences between successive intervals,” “the percentage,” “the standard deviation of the average intervals computed over short periods.” The recited terms lack antecedent basis, and are therefore indefinite. Additionally, the claim’s recitation of “such as” is indefinite language. It is unclear what is considered claimed subject matter.
Regarding claim 16, the claim recites “the series,” the power, “the low frequency,” “the high frequency range,” the normalized power in the low frequency range,” “the normalized power in the high frequency range,” and the ratio of the power.” The recited terms lack antecedent basis, and are therefore indefinite. Additionally, the claim’s recitation of “such as” is indefinite language. It is unclear what is considered claimed subject matter.
Regarding claim 17, the claim recites “the series,” “the approximate entropy,” “the sample entropy,” and “the coefficients…provided by the detrended fluctuation analysis.” The recited terms lack antecedent basis, and are therefore indefinite. Additionally, the claim’s recitation of “such as” is indefinite language. It is unclear what is considered claimed subject matter.
Regarding claim 18, the claim recites “the energy content and energy ratios” and “the series.” The recited terms lack antecedent basis, and are therefore indefinite.
Regarding claim 19, the claim recites “such as.” This is indefinite language and it is unclear what is considered claimed subject matter.
Regarding claim 20, the claim recites “the value of the level of sepsis,” “the value of the heart rate,” “the value of the burst suppression ratio (BSR),” “the value of the impedance,” “the value of a signal quality index,” “the value of the level of battery,” and “the trend of any value of the calculated indices.” The recited terms lack antecedent basis, and are therefore indefinite.
Further regarding claim 20, the applicant recites “a microprocessor configured to present an output to a display, among others, which may be any one of the following:”. It is unclear what “others” references. As recited, among others may refer to the locations where an output is displayed, or it could refer to the types of outputs. “Others,” for examination purposes, is interpreted as the types of outputs on the display.
Regarding claims 3, 4, 6, 13-17, and 19, the phrase "such as" renders the claim indefinite because it is unclear whether the limitations following the phrase are part of the claimed invention. (See MPEP § 2173.05(d)) (Additionally, see above).
For examination purposes, claims reciting “such as” will be interpreted as being followed by claimed subject matter.
Regarding claim 19, a broad range or limitation together with a narrow range or limitation that falls within the broad range or limitation (in the same claim) may be considered indefinite if the resulting claim does not clearly set forth the metes and bounds of the patent protection desired. See MPEP § 2173.05(c). In the present instance, claim 19 recites the broad recitation “or any other prediction model.” and the claim also recites “a prediction model which can be either a linear regression, a logistic regression, a fuzzy logic classifier, a neural network, a hybrid between a fuzzy logic system and a neural network such as an adaptive neuro fuzzy inference system,” which is the narrower statement of the range/limitation. The claim(s) are considered indefinite because there is a question or doubt as to whether the feature introduced by such narrower language is (a) merely exemplary of the remainder of the claim, and therefore not required, or (b) a required feature of the claims.
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.
Section 33(a) of the America Invents Act reads as follows:
Notwithstanding any other provision of law, no patent may issue on a claim directed to or encompassing a human organism.
Claim 11 is rejected under 35 U.S.C. 101 and section 33(a) of the America Invents Act as being directed to or encompassing a human organism. See also Animals - Patentability, 1077 Off. Gaz. Pat. Office 24 (April 21, 1987) (indicating that human organisms are excluded from the scope of patentable subject matter under 35 U.S.C. 101).
Regarding claim 11, the claim is to the apparatus of claim 10 and requires electrodes positioned on the forehead (line 2) and above the ear (line 3), which requires a human organism.
Claims 1-20 rejected under 35 U.S.C. 101 because the claimed invention is directed towards an abstract idea without significantly more.
Step 1
Independent claim 1 recites a process (i.e., method).
Step 2A, Prong 1
Regarding claim 1, the following steps recite an abstract idea:
“Detecting the location of the QRS complexes in the electrocardiogram” is a mental process when given its broadest reasonable interpretation. As discussed in MPEP 2106.04(a)(2)(II), the mental process grouping includes observations, evaluation, judgments, and opinions. In this case, a human could observe an electrocardiogram and detect the location of the QRS complex.
“Building the interbeat interval series used for the calculation of the heart rate variability and the heart rate n-variability” ” is a mental process when given its broadest reasonable interpretation. As discussed in MPEP 2106.04(a)(2)(II), the mental process grouping includes observations, evaluation, judgments, and opinions. In this case, a human could build an interbeat interval series based on the evaluating the electrocardiogram and collecting the data to use it in a calculation of heart rate variability and heart rate n-variability.
“Calculating the time domain features from the electroencephalogram” is a mathematical concept when given its broadest reasonable interpretation. As discussed in MPEP 2106.04(a)(2)(I), the mathematical concepts grouping is defined as mathematical relationships, mathematical formulas or equations, and mathematical calculations. In this case, a human could calculate the time domain features from the data provided by the electroencephalogram.
“Calculating the frequency domain features from the electroencephalogram” is a mathematical concept when given its broadest reasonable interpretation. As discussed in MPEP 2106.04(a)(2)(I), the mathematical concepts grouping is defined as mathematical relationships, mathematical formulas or equations, and mathematical calculations. In this case, a human could calculate the frequency domain features from the data provided by the electroencephalogram.
“Calculating the frequency domain features from the electrocardiogram” is a mathematical concept when given its broadest reasonable interpretation. As discussed in MPEP 2106.04(a)(2)(I), the mathematical concepts grouping is defined as mathematical relationships, mathematical formulas or equations, and mathematical calculations. In this case, a human could calculate the frequency domain features from the data provided by the electrocardiogram.
“Calculating the heart rate from the location of the QRS complex” ” is a mathematical concept when given its broadest reasonable interpretation. As discussed in MPEP 2106.04(a)(2)(I), the mathematical concepts grouping is defined as mathematical relationships, mathematical formulas or equations, and mathematical calculations. In this case, a human could calculate the heart rate from the location of the QRS complex by calculating the time intervals between points on the QRS complex.
“Calculating the time domain features from the heart rate variability and the heart rate n-variability” is a mathematical concept when given its broadest reasonable interpretation. As discussed in MPEP 2106.04(a)(2)(I), the mathematical concepts grouping is defined as mathematical relationships, mathematical formulas or equations, and mathematical calculations. In this case, a human could calculate the time domain features from the heart rate variability and the heart rate n-variability.
“Calculating the frequency domain features from the heart rate variability and heart rate n-variability” ” is a mathematical concept when given its broadest reasonable interpretation. As discussed in MPEP 2106.04(a)(2)(I), the mathematical concepts grouping is defined as mathematical relationships, mathematical formulas or equations, and mathematical calculations. In this case, a human could calculate the frequency domain features from the heart rate variability and the heart rate n-variability.
“Calculating the nonlinear features from the heart rate variability and heart rate n-variability” is a mathematical concept when given its broadest reasonable interpretation. As discussed in MPEP 2106.04(a)(2)(I), the mathematical concepts grouping is defined as mathematical relationships, mathematical formulas or equations, and mathematical calculations. In this case, a human could calculate the non-linear features from the heart rate variability and the heart rate n-variability.
“Calculating the cross correlation and the mutual information between the electroencephalogram and the electrocardiogram, the heart rate variability and the n-variability” ” is a mathematical concept when given its broadest reasonable interpretation. As discussed in MPEP 2106.04(a)(2)(I), the mathematical concepts grouping is defined as mathematical relationships, mathematical formulas or equations, and mathematical calculations. In this case, a human could calculate the cross correlation and the mutual information between the electroencephalogram and the electrocardiogram, the heart rate variability and the n-variability.
“Using a prediction model to combine at least four parameters derived from the electroencephalogram and the electrocardiogram into a final index of sepsis” is a mathematical concept abstract idea when given its broadest reasonable interpretation. As discussed in MPEP 2106.04(a)(2)(I), the mathematical concepts grouping is defined as mathematical relationships, mathematical formulas or equations, and mathematical calculations.. In this case, predictions are made from a combination of parameters derived from the electroencephalogram and electrocardiogram data, and then the data is used in various functions for the predictions combined into an index to predict sepsis.
Step 2A, Prong 2
Regarding claim 1, the abstract idea is not integrated into a practical application. The following elements do not add any meaningful limitation to the abstract idea:
“measuring the electroencephalogram” is recited at a high level of generality. The measuring of the electroencephalogram amounts to insignificant extra-solution activity in that it is a method of gathering and collecting data [MPEP 2106.05(b)].
“measuring the electrocardiogram” is recited at a high level of generality. The measuring of the electrocardiogram amounts to insignificant extra-solution activity in that it is a method of gathering and collecting data [MPEP 2106.05(b)].
The preamble of claim 1 recites “a method for determining the level of sepsis by combination of parameters extracted from an electroencephalogram (3) and an electrocardiogram (4).” The preamble of merely defines the statutory category (a method) while linking the method to a field of use [MPEP 2106.05(d)(I)] and does not amount to meaningful integration of the abstract idea into a practical application.
Step 2B
The additional elements of claim 1, when considered either individually or in an ordered combination, are not enough to qualify as significantly more than the abstract idea.
“measuring the electroencephalogram” is recited at a high level of generality. The measuring of the electroencephalogram amounts to insignificant extra-solution activity in that it is a method of gathering and collecting data [MPEP 2106.05(g)].
“measuring the electrocardiogram” is recited at a high level of generality. The measuring of the electrocardiogram amounts to insignificant extra-solution activity in that it is a method of gathering and collecting data [MPEP 2106.05(g)].
The preamble of claim 1 recites “a method for determining the level of sepsis by combination of parameters extracted from an electroencephalogram (3) and an electrocardiogram (4).” The preamble of merely defines the statutory category (a method) while linking the method to a field of use [MPEP 2106.05(h)] and does not amount to meaningful integration of the abstract idea into a practical application.
Dependent Claim(s)
Claim 2 further defines a limitation of an abstract idea mental process. A human could construct a series of individual heart beats and a series of intervals for the cases. It also recites a mathematical concept in that a human could perform a summation of the intervals.
Claim 3-7 further define a mathematical concepts that could be performed by a human.
Claim 8 further defines an abstract idea mathematical concept by limiting the types of prediction models.
Claim 9 further recites the implementation of an abstract idea into generic computer structure (a microprocessor).
Step 1
Independent claim 10 recites a machine (i.e., an apparatus).
Step 2A, Prong 1
Regarding claim 10, the following limitations recite an abstract idea:
“Detect the location of the QRS complexes in the electrocardiogram” is a mental process when given its broadest reasonable interpretation. As discussed in MPEP 2106.04(a)(2)(II), the mental process grouping includes observations, evaluation, judgments, and opinions. In this case, a human could observe an electrocardiogram and detect the location of the QRS complex.
“Build the interbeat interval series used for the calculation of the heart rate variability and the heart rate n-variability” ” is a mental process when given its broadest reasonable interpretation. As discussed in MPEP 2106.04(a)(2)(II), the mental process grouping includes observations, evaluation, judgments, and opinions. In this case, a human could build an interbeat interval series based on the evaluating the electrocardiogram and collecting the data to use it in a calculation of heart rate variability and heart rate n-variability.
“Calculate the time domain features from the electroencephalogram” is a mathematical concept when given its broadest reasonable interpretation. As discussed in MPEP 2106.04(a)(2)(I), the mathematical concepts grouping is defined as mathematical relationships, mathematical formulas or equations, and mathematical calculations. In this case, a human could calculate the time domain features from the data provided by the electroencephalogram.
“Calculate the frequency domain features from the electroencephalogram” is a mathematical concept when given its broadest reasonable interpretation. As discussed in MPEP 2106.04(a)(2)(I), the mathematical concepts grouping is defined as mathematical relationships, mathematical formulas or equations, and mathematical calculations. In this case, a human could calculate the frequency domain features from the data provided by the electroencephalogram.
“Calculate the frequency domain features from the electrocardiogram” is a mathematical concept when given its broadest reasonable interpretation. As discussed in MPEP 2106.04(a)(2)(I), the mathematical concepts grouping is defined as mathematical relationships, mathematical formulas or equations, and mathematical calculations. In this case, a human could calculate the frequency domain features from the data provided by the electrocardiogram.
“Calculate the heart rate from the location of the QRS complex” ” is a mathematical concept when given its broadest reasonable interpretation. As discussed in MPEP 2106.04(a)(2)(I), the mathematical concepts grouping is defined as mathematical relationships, mathematical formulas or equations, and mathematical calculations. In this case, a human could calculate the heart rate from the location of the QRS complex by calculating the time intervals between points on the QRS complex.
“Calculate the time domain features from the heart rate variability and the heart rate n-variability” is a mathematical concept when given its broadest reasonable interpretation. As discussed in MPEP 2106.04(a)(2)(I), the mathematical concepts grouping is defined as mathematical relationships, mathematical formulas or equations, and mathematical calculations. In this case, a human could calculate the time domain features from the heart rate variability and the heart rate n-variability.
“Calculate the frequency domain features from the heart rate variability and heart rate n-variability” ” is a mathematical concept when given its broadest reasonable interpretation. As discussed in MPEP 2106.04(a)(2)(I), the mathematical concepts grouping is defined as mathematical relationships, mathematical formulas or equations, and mathematical calculations. In this case, a human could calculate the frequency domain features from the heart rate variability and the heart rate n-variability.
“Calculate the nonlinear features from the heart rate variability and heart rate n-variability” is a mathematical concept when given its broadest reasonable interpretation. As discussed in MPEP 2106.04(a)(2)(I), the mathematical concepts grouping is defined as mathematical relationships, mathematical formulas or equations, and mathematical calculations. In this case, a human could calculate the non-linear features from the heart rate variability and the heart rate n-variability.
“Calculate the cross correlation and the mutual information between the electroencephalogram and the electrocardiogram, the heart rate variability and the n-variability” ” is a mathematical concept when given its broadest reasonable interpretation. As discussed in MPEP 2106.04(a)(2)(I), the mathematical concepts grouping is defined as mathematical relationships, mathematical formulas or equations, and mathematical calculations. In this case, a human could calculate the cross correlation and the mutual information between the electroencephalogram and the electrocardiogram, the heart rate variability and the n-variability.
“Use a prediction model to combine at least four parameters derived from the electroencephalogram and the electrocardiogram into a final index of sepsis” is a mental process when given its broadest reasonable interpretation As discussed in MPEP 2106.04(a)(2)(I), the mathematical concepts grouping is defined as mathematical relationships, mathematical formulas or equations, and mathematical calculations. Data from an EEG and ECG is used in various functions of the prediction model, and then the predictions are combined into an index to predict sepsis.
Step 2A, Prong 2
Regarding claim 10, the abstract idea is not integrated into a practical application. The following elements do not add any meaningful limitation to the abstract idea:
“a sensor for measuring the electroencephalogram” is recited at a high level of generality. The sensor for measuring the electroencephalogram amounts to insignificant extra-solution activity in that it is a gathering and collecting data [MPEP 2106.05(g)].
“a sensor for measuring the electrocardiogram” is recited at a high level of generality. The sensor for measuring the electrocardiogram amounts to insignificant extra-solution activity in that it is a method of gathering and collecting data [MPEP 2106.05(g)].
“a microprocessor configured to” is a generic computer tool used to perform mental processes and mathematical calculations [MPEP 2106.05(f)].
The preamble of claim 1 recites “An apparatus for determining a level of sepsis by combination of parameters extracted from an electroencephalogram (3) and an electrocardiogram (4).” The preamble of merely defines the statutory category (an apparatus) while linking the method to a field of use [MPEP 2106.05(h)] and does not amount to meaningful integration of the abstract idea into a practical application.
Step 2B
The additional elements of claim 1, when considered either individually or in an ordered combination, are not enough to qualify as significantly more than the abstract idea.
“a sensor for measuring the electroencephalogram” is recited at a high level of generality. The sensor for measuring the electroencephalogram amounts to insignificant extra-solution activity in that it is a gathering and collecting data [MPEP 2106.05(g)].
“a sensor for measuring the electrocardiogram” is recited at a high level of generality. The sensor for measuring the electrocardiogram amounts to insignificant extra-solution activity in that it is a method of gathering and collecting data [MPEP 2106.05(g)].
“a microprocessor configured to” is a generic computer tool used to perform mental processes and mathematical calculations [MPEP 2106.05(f)].
The preamble of claim 1 recites “an apparatus for determining a level of sepsis by combination of parameters extracted from an electroencephalogram (3) and an electrocardiogram (4).” The preamble of merely defines the statutory category (an apparatus) while linking the method to a field of use [MPEP 2106.05(h)] and does not amount to significantly more than the abstract idea.
Dependent claim(s)
Claim 11 further limits the senor used for extra-solution activity of data gathering.
Claim 12 further defines limitations of an abstract idea mental process. A human could construct a series of individual heart beats and a series of intervals for the cases.
Claim 13-18 further define a mathematical concepts.
Claim 19 further defines an abstract idea mathematical concepts by limiting the types of prediction models. Each of the recited prediction model performs functions that are mathematical concepts.
Claim 20 further recites the implementation of an abstract idea into generic computer structure (a microprocessor). The limitation of “an output to display” is considered insignificant post-solution activity.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1-8 are rejected under 35 U.S.C. 103 as being unpatentable over Jensen (US 20160374581 A1, “Jensen A”), Jensen et al. (US 20180000409 A1, “Jensen B”), and Liu et al. (Heart rate n-variability (HRnV) measures for prediction of mortality in sepsis patients presenting at the emergency department; Pub. Date: August 30, 2021, “Liu”).
Regarding claim 1, Jensen A discloses a method for determining the level of sepsis (para. [0008]; “inflammation index”; para. [0049]; “The inflammatory cascade can be very aggressive towards the patient's own tissue leading to sepsis, even death.”) by combination of parameters (Abstract; “combining at least 3 extracted parameters”) extracted from an electroencephalogram (3) and an electrocardiogram (4) (abstract; “a) sensor for measuring electroencephalogram; b) sensor for measuring the electrocardiogram”) comprising the following steps: a.) measuring the electroencephalogram (Abstract; “sensor for measuring electroencephalogram); b.)measuring the electrocardiogram (abstract; “sensor for measuring the electrocardiogram.”); c.) detecting the location of the QRS complexes in the electrocardiogram (para. [0058]; “The present invention records the electrocardiogram (ECG), extracts the R-R interval and other features from the ECG, such as intervals between p,q,r and t peaks.”; The R peaks are included in the QRS complex); d.) building the interbeat interval series used for the calculation of the heart rate variability (para. [0035]; “The term “RR intervals” refer to the time between successive R-peaks in the ECG. From the RR intervals the following parameters are extracted.”); f.) Calculating the frequency domain features from the electroencephalogram (para. [0064]; “the frequency with the highest energy content in FFT spectrum of the EEG.”); g.) Calculating the frequency domain features from the electrocardiogram (para. [0058]; “Furthermore an FFT of the RR interval is carried out, from which the Heart Rate Variability (HRV) is defined”); h.) Calculating the heart rate from the location of the QRS complex (Table 1: Heart rate is shown as the reciprocal of the mean of all RR intervals (a feature of the QRS complex). “The RR intervals are derived from the R intervals of a QRS complex”); j.) Calculating the frequency domain features from the heart rate variability and heart rate n-variability. (para. [0058]; “From the HRV, different frequency bands are extracted for example HF and LF, see table 1.”); l.) Calculating the mutual information (para. [0063]; “Here the EEG equal X while ECG equals Y. The information transfer from signal X to Y is measured by the difference of two mutual information values”), between the electroencephalogram and the electrocardiogram, the heart rate variability and the n-variability.; m.) Using a prediction model to combine at least four parameters derived from the electroencephalogram and the electrocardiogram into a final index of sepsis. (Abstract; “combining at least 3 extracted parameters using an Adaptive Neuro Fuzzy inference system (ANFIS) or any other fuzzy reasoner into a final index of cardiac output; para. [0011]; “ANFIS is a hybrid between a fuzzy logic system and a neural network.”; para. [0042]; “ANFIS1 (710) takes as input the parameters extracted from the voltage plethysmogram, in a preferred embodiment there are at least 3 inputs, as shown in FIG. 7, however more inputs could be included”;). Although Jensen A does not disclose that the index is an index of sepsis, Jensen A discloses a final inflammation index, which is emphasized as a major indicator of sepsis. (para. [0049]; “Mechanisms of inflammation induce changes in behavior and body constituting inflammatory syndrome associated with illness. Initially and under control, inflammation promotes healing through the molecular and cellular. But when not properly compensated, the inflammation can have serious consequences for the patient. The inflammatory cascade can be very aggressive towards the patient's own tissue leading to sepsis, even death.) However, Jensen does not disclose the step: e.) Calculating the time domain features from the electroencephalogram. Jensen also fails to disclose calculating a cross-correlation. Although Jensen A does disclose the steps of calculating heart rate variability, Jensen A does not disclose the doing the same calculations for heart rate n-variability. Lastly, Jensen A does not disclose that the index is an index of sepsis.
In US 20180000409 A1, Jensen B, in the same field of measuring and comparing EEG and ECG signals and inputting them into a predictive model, discloses an apparatus and method for predicting values on a nociception index. Jensen B discloses the steps: e.) Calculating the time domain features from the electroencephalogram; (para. [0062]; “The frequency bands (3) are extracted from the time domain of the EEG”); Jensen also discloses calculating the cross-correlation between the electroencephalogram and the electrocardiogram (para. [0069]; “The mutual information, Fokker-Planck drift and diffusion coefficients and cross correlation are calculated for the frequencies calculated of the EEG, EMG and ECG”); m) combining 4 parameters (para. [0011]; “a combination of additional parameters of HR, SpO2, ICG, EEG and facial EMG is applied.”; The previous reference only discloses that the prediction model is capable of having 4 inputs. This reference discloses 4 inputs.). However, Jensen B does not disclose performing the same calculations with heart rate n-variability.
Liu, in the same field of endeavor of calculating heart rate variability metrics and using them in a predictive model for sepsis prediction, discloses a method of calculating parameters for heart rate n-variability. Liu discloses steps i.) Calculating the time domain features from the heart rate variability and the heart rate n-variability (pg. 6, para. (2); “Among time domain parameters such as mean NN and SDNN, HR.sub.nV and HR.sub.nV.sub.m values are generally directly proportional to n and increase when n increases. HR.sub.2V SampEn and HR3V SampEn were considerably larger than SampEn parameters of HRV, HR2V1, HR3V1, and HR3V2.”) and k.) Calculating the nonlinear features from the heart rate n-variability (pg. 4, para. (1); “With newly generated RRnI sequences, traditional time and frequency domains, and nonlinear analyses [27,28] are applied to calculate HRnV parameters”). Additonally, Liu discloses methods of building interbeat interval series for the calculation of heart rate n-variability (step (d)) (pg. 3, para. (3); “RRnI”; “a new type of RRI.”), as well as calculating frequency domain features from heart rate n-variability (step j)(Table 2). Lastly, Liu discloses using heart rate n-variability in a prediction model (pg. 8, para. (1) ; “The final multivariable predictive model consisted of four vital signs, two traditional HRV parameters, and 15 novel HRnV parameters.”)
It would have been obvious to one of ordinary skill in the art before the effective filling date to combine the methods of Jensen A of measuring and calculating EEG and ECG metrics and inputting them into a prediction model with the methods of Jensen B where time domain features are also calculated and a cross-correlation is performed between the EEG and ECG signals. A cross-correlation is a known technique that could be applied to Jensen A’s methods to improve means of signal comparison between the EEG and ECG. Further, Jensen A is comparing the signals to find mutual information, and using cross-correlation method would be an obvious technique to further improve the method. Further, to use this cross-correlation method, one would have to obtain the time domain features of the EEG, which is a step Jensen A already performs for the ECG. Therefore, it would have been obvious to repeat this step to use in the cross-correlation calculation. Lastly, it would have been obvious to increase the number of inputs to 4 since Jensen already disclosed that the prediction model can use more than 3 inputs.
In addition to combining Jensen A and Jensen B, it would have been obvious for one of ordinary skill in the art to include the steps involving calculating heart rate n-variability, as disclosed by Liu, in the methods of calculating heart rate variability. Heart-rate n-variability is a known technique that improves on the previous technique of measuring heart rate variability by providing a more detailed analysis of heart rate variability and enhanced prognostic information (Liu; pg. 2, para. [3]). As disclosed by Jensen A and Jensen B, the steps of the method involving calculations of heart-rate variability are previously disclosed, and improving these steps with the addition of heart-rate n-variability would have been obvious.
Regarding claim 2, the combination of Jensen A and B and Liu disclose the method according to claim 1 (see above). Jensen A discloses wherein step d is characterized by the construction of series of the consecutive individual interbeat intervals in the case heart rate variability (para. [0035]). Liu discloses the construction of series of intervals resulting from the sum of multiple consecutive interbeat intervals, with or without overlapping, in the case of heart rate n-variability (pg. 2, para. (3); “The proposed HRnV has two measures—HRnV and HRnVm. HRnV is derived from non-overlapping R-R intervals, while HRnVm is computed from overlapping R-R intervals.”)
It would have been obvious to one of ordinary skill in the art before the effective filing date to combine the method of constructing series of intervals as disclosed in Jensen with the series of overlapping or non-overlapping intervals for heart rate n-variability of Liu. The construction of intervals for heart rate n-variability is a known technique as disclosed by Liu, and using this technique in conjunction with Liu is an obvious improvement of the previous method that only uses heart rate variability.
Regarding claim 3, the combination of Jensen A and B and Liu disclose the method according to claim 1 (see above). Further, Jensen B discloses wherein step g is characterized by the extraction of frequency domain features from the electrocardiogram (4) such as the energy content in frequency bands of the electrocardiogram (para. [0062]; “The mutual information, Fokker-Planck drift and diffusion coefficients and cross correlation are calculated for the frequency bands of the EEG and ECG.) and the energy ratios across pairs of frequency bands of the electrocardiogram (para. [0069]; “A Fast Fourier Transform (FFT) is applied to the EEG and the energy in frequency bands are defined. From that ratios are calculated which are used as input to the classifier. The mutual information, Fokker-Planck drift and diffusion coefficients and cross correlation are calculated for the frequencies calculated of the EEG, EMG and ECG.”) Additionally, Liu discloses wherein step g is characterized by the extraction of frequency domain features from the electrocardiogram (4) such as the energy content in frequency bands of the electrocardiogram and the energy ratios across pairs of frequency bands of the electrocardiogram (see table 2 where Liu describes the extraction of HF, LF, voltage, and other energy and frequency contents from HR variability and HR n-variability calculations).
It would have been obvious for one of ordinary skill in the art before the effective filing date to combine the methods disclosed by the combination of Jensen A and B and Liu with the methods of extracting energy content and energy ratios from the ECG of Jensen B. Using the energy content and ratios is a known technique in the art as an input for predictive models, as demonstrated by Jensen B. Therefore, it would have been obvious to use this known method of calculating data as an input into a predictive model. In addition, it would have been obvious for one to extract frequency domain features from the ECG as in the case with Liu and combine the extraction with the methods of claim 1. The extraction of frequency domain features for implementation in a predictive model are well known techniques in the art, as demonstrated by Liu.
Regarding claim 4, the combination of Jensen A and B and Liu disclose the method according to claim 1 (see above). Further, Liu discloses wherein step i is characterized by the extraction of time domain features from the series of intervals considered in both heart rate variability and heart rate n-variability such as the root mean square differences between successive intervals (RMSSD), (Table 2) the standard deviation of the differences between successive intervals (SDSD) (Table 2), the percentage of successive intervals differing by more than 50ms (pNN50) (Table 2), the standard deviation of the intervals typically computed over a 24-hour period (SDNN) (Table 2), or the standard deviation of the average intervals computed over short periods, typically 5 minutes (SDANN)(Table 2).
It would have been obvious to combine the methods disclosed by the combination of Jensen A and B and Liu of claim 1 with the defined extraction of time domain features of Liu. The extracted features are known elements of time domain features in both heart rate variability and heart rate n-variability, as demonstrated by Liu. Further, it would have been obvious to use these extracted features in a predictive model for sepsis as in the case of Liu.
Regarding claim 5, the combination of Jensen A and B and Liu disclose the method according to claim 1 (see above). Further, Liu discloses wherein step j is characterized by the extraction of frequency domain features from the series of intervals considered in both heart rate variability and heart rate n-variability (table 2; High frequency power, low frequency power, and other frequency parameters shown for HR variability and HR v-variability).
It would have been obvious to combine the methods disclosed by the combination of Jensen A and B and Liu of claim 1 with the defined extraction of frequency domain features of Liu. The extracted features are known elements of frequency domain features in both heart rate variability and heart rate n-variability, as demonstrated by Liu. Further, it would have been obvious to use these extracted features in a predictive model for sepsis as in the case of Liu.
Regarding claim 6, the combination of Jensen A and B and Liu disclose the method according to claim 1 (see above). Liu discloses wherein step k is characterized by the extraction of nonlinear features from the series of intervals considered in both heart rate variability and heart rate n-variability such as the approximate entropy (ApEn) (table 2), the sample entropy (SampEn)(table 2) or the coefficients α1 and α2 provided by the detrended fluctuation analysis (DFA)(both included in table 2; Includes all of the non-linear features for both heart rate variability and heart rate n-variability).
It would have been obvious to combine the methods disclosed by the combination of Jensen A and B and Liu of claim 1 with the extraction of nonlinear features of Liu. The extracted features are known elements in both heart rate variability and heart rate n-variability, as demonstrated by Liu. Further, it would have been obvious to use these extracted features in a predictive model for sepsis, as in the case of Liu, to improve the method of predicting sepsis.
Regarding claim 7, the combination of Jensen A and B and Liu disclose the method according to claim 1 (see above). Further, Jensen B discloses wherein step l is characterized by calculating features derived from the cross-correlation and mutual information functions between the energy content and energy ratios of the electroencephalogram (3) and the energy content and energy ratios of the electrocardiogram (4) (para. [0069]; “A Fast Fourier Transform (FFT) is applied to the EEG and the energy in frequency bands are defined. From that ratios are calculated which are used as input to the classifier. The mutual information, Fokker-Planck drift and diffusion coefficients and cross correlation are calculated for the frequencies calculated of the EEG, EMG and ECG”). Additionally, Liu discloses where calculating features from the series of intervals considered in both heart rate variability and heart rate n-variability (table 2 describes DFA coefficients derived from heart rate variability and heart rate n variability).
It would have been obvious to one of ordinary skill in the art to combine the methods of claim 1 as disclosed in the combination of Jensen A and B and Liu to include the methods of calculating energy content and ratio features derived from the EEG, ECG, heart rate variability, and heart rate n-variability as disclosed in Liu and Jensen B. Performing a cross-correlation, as disclosed by Jensen, is a well known technique in the art that further improves the method of comparing signals by analyzing the mutual information shared between them. Further, it would have been obvious to include the well known technique of heart rate n-variability in this calculation and comparing the features obtained with the heart rate variability features. Doing so would improve the method of calculating input for a predictive model for sepsis, as disclosed in Liu.
Regarding claim 8, the combination of Jensen A and B and Liu disclose the method according to claim 1. Jensen B further discloses wherein step m is characterized by the use of a prediction model which can be either a linear regression, a logistic regression, a fuzzy logic classifier, a neural network, a hybrid between a fuzzy logic system and a neural network such as an adaptive neuro fuzzy inference system, or any other prediction model (para. [0060]; “The parameters extracted from EEG, EMG, and HRV are all used as input to the classifier (13) which could be either a linear regression, a logistic regression, a fuzzy logic classifier, a neural network or a hybrid between a fuzzy logic system and a neural network such as an Adaptive Neuro Fuzzy Inference System (ANFIS)”).
It would have been obvious to one of ordinary skill in the art before the effective filing date to include the characterization of the predictive model, as disclosed by Jensen, with the methods of claim 1. It would have been obvious to try one of the listed predictive models of claim 8 since there are a finite number of predictive models available. Further, Jensen B discloses the same optional predictive models, meaning they are well known in the art. Jensen uses the predictive model to predict an index from EEG and ECG data as well.
Claim(s) 9-20 are rejected under 35 U.S.C. 103 as being unpatentable over Jensen (US 20160374581 A1, “Jensen A”), Jensen et al. (US 20180000409 A1, “Jensen B”), Liu et al. (Heart rate n-variability (HRnV) measures for prediction of mortality in sepsis patients presenting at the emergency department; Pub. Date: August 30, 2021, “Liu”), and Page (US 20210065888 A1, “Page”).
Regarding claim 9, the combination of Jensen A and B and Liu disclose the method according to claim 1 (see above). However, the combination of Jensen A and B and Liu do not disclose the method implemented into a microprocessor where the output to a display, among others, may be any of the following: one or several EEG signals, one or several ECG signals, the value of the level of sepsis, the value of the heart rate (HR), the value of the burst suppression ratio (BSR), the value of the impedance of the electrodes (IMP), the value of a signal quality index (SQI), the value of the level of the battery (BAT) or the trend of any of the calculated indices over time.
Page, in the same field of endeavor of monitoring medical conditions, discloses a device for monitoring patient health, including risk of sepsis. Page discloses a microprocessor (para. [0062]; “The processor(s) may be any suitable processor, processing unit, or microprocessor, for example.”) where the output to a display (para. [0058]; “display (e.g. screen or monitor)”), among others, may be any of the following: one or several EEG signals, one or several ECG signals, the value of the level of sepsis, the value of the heart rate (HR) (para. [0108]; “The in-room GUI 2100 includes a plurality of patient monitoring tiles, such as patient monitoring tile 2114 (which is displaying patient heart rate both as a representative ECG waveform and as a most-recently determined value.”), the value of the burst suppression ratio (BSR), the value of the impedance of the electrodes (IMP), the value of a signal quality index (SQI), the value of the level of the battery (BAT) or the trend of any of the calculated indices over time.
It would have been obvious to one of ordinary skill in the art before the effective filing date to combine the methods of claim 1 with the processor and display to display ECG signals and heart rate as disclosed by Page. A microprocessor is a well-known computer component for ECG processing as it is used in Page. Additionally, including a display is an obvious improvement that would allow the person performing the methods of claim one to easily visualize the data. Lastly, including the following outputs on the display is a well-known technique for ECG data visualization. Applying these well-known techniques would have resulted in obvious improvements of signal processing and data visualization.
Regarding claim 10, Jensen A discloses an apparatus for determining a level of sepsis ((para. [0008]; “inflammation index”; para. [0049]; “The inflammatory cascade can be very aggressive towards the patient's own tissue leading to sepsis, even death.”) .”) by combination of parameters (Abstract; “combining at least 3 extracted parameters”) extracted from an electroencephalogram (3) and an electrocardiogram (4) (abstract; “a) sensor for measuring electroencephalogram; b) sensor for measuring the electrocardiogram”) comprising: a.) a sensor for measuring the electroencephalogram (Abstract; “sensor for measuring electroencephalogram); b.) a sensor measuring the electrocardiogram (abstract; “sensor for measuring the electrocardiogram.”); c.) a microprocessor configured to:
i.) detect the location of the QRS complexes in the electrocardiogram (para. [0058]; “The present invention records the electrocardiogram (ECG), extracts the R-R interval and other features from the ECG, such as intervals between p,q,r and t peaks.”; The R peaks are included in the QRS complex); ii.) building the interbeat interval series used for the calculation of the heart rate variability (para. [0035]; “The term “RR intervals” refer to the time between successive R-peaks in the ECG. From the RR intervals the following parameters are extracted.”); iv.) Calculating the frequency domain features from the electroencephalogram (para. [0064]; “the frequency with the highest energy content in FFT spectrum of the EEG.”); v.) Calculating the frequency domain features from the electrocardiogram (para. [0058]; “Furthermore an FFT of the RR interval is carried out, from which the Heart Rate Variability (HRV) is defined”); vi.) Calculating the heart rate from the location of the QRS complex (Table 1: Heart rate is shown as the reciprocal of the mean of all RR intervals (a feature of the QRS complex). “The RR intervals are derived from the R intervals of a QRS complex”); viii.) Calculating the frequency domain features from the heart rate variability and heart rate n-variability. (para. [0058]; “From the HRV, different frequency bands are extracted for example HF and LF, see table 1.”); x.) Calculating the mutual information (para. [0063]; “Here the EEG equal X while ECG equals Y. The information transfer from signal X to Y is measured by the difference of two mutual information values”), between the electroencephalogram and the electrocardiogram, the heart rate variability and the n-variability.; xi.) Using a prediction model to combine at least four parameters derived from the electroencephalogram and the electrocardiogram into a final index of sepsis. (Abstract; “combining at least 3 extracted parameters using an Adaptive Neuro Fuzzy inference system (ANFIS) or any other fuzzy reasoner into a final index of cardiac output; para. [0011]; “ANFIS is a hybrid between a fuzzy logic system and a neural network.”; para. [0042]; “ANFIS1 (710) takes as input the parameters extracted from the voltage plethysmogram, in a preferred embodiment there are at least 3 inputs, as shown in FIG. 7, however more inputs could be included”;). Although Jensen does not disclose that the index is an index of sepsis, Jensen discloses a final inflammation index, which is a major indicator of sepsis. (para. [0049]; “Mechanisms of inflammation induce changes in behavior and body constituting inflammatory syndrome associated with illness. Initially and under control, inflammation promotes healing through the molecular and cellular. But when not properly compensated, the inflammation can have serious consequences for the patient. The inflammatory cascade can be very aggressive towards the patient's own tissue leading to sepsis, even death.) However, Jensen does not disclose the step: iii.) Calculating the time domain features from the electroencephalogram. Jensen also fails to disclose calculating a cross-correlation. Although Jensen does disclose the steps of calculating heart rate variability, Jensen does not disclose doing the same calculations for heart rate n-variability. Lastly, Jensen A does not disclose an output display or a microprocessor configured to perform the steps.
In US 20180000409 A1, Jensen B discloses the steps: e.) Calculating the time domain features from the electroencephalogram; (para. [0062]; “The frequency bands (3) are extracted from the time domain of the EEG”); Jensen also discloses calculating the cross-correlation between the electroencephalogram and the electrocardiogram (para. [0069]; “The mutual information, Fokker-Planck drift and diffusion coefficients and cross correlation are calculated for the frequencies calculated of the EEG, EMG and ECG”); m) combining 4 parameters (para. [0011]; “a combination of additional parameters of HR, SpO2, ICG, EEG and facial EMG is applied.”; The previous reference only discloses that the prediction model is capable of having 4 inputs. This reference discloses 4 inputs.). However, Jensen B does not disclose performing the same calculations with heart rate n-variability, or that a microprocessor is configured to perform the steps.
It would have been obvious to one of ordinary skill in the art before the effective filling date to combine the methods of Jensen A of measuring and calculating EEG and ECG metrics and inputting them into a prediction model with the methods of Jensen B where time domain features are also calculated and a cross-correlation is performed between the EEG and ECG signals. A cross-correlation is a known technique that could be applied to Jensen A’s methods to improve means of signal comparison between the EEG and ECG. Further, this method would improve the previous method of comparing signals using mutual information, as disclosed in Jensen B.
Liu discloses steps i.) Calculating the time domain features from the heart rate variability and the heart rate n-variability (pg. 6, para. (2); “Among time domain parameters such as mean NN and SDNN, HR.sub.nV and HR.sub.nV.sub.m values are generally directly proportional to n and increase when n increases. HR.sub.2V SampEn and HR3V SampEn were considerably larger than SampEn parameters of HRV, HR2V1, HR3V1, and HR3V2.”) and k.) Calculating the nonlinear features from the heart rate n-variability (pg. 4, para. (1); “With newly generated RRnI sequences, traditional time and frequency domains, and nonlinear analyses [27,28] are applied to calculate HRnV parameters”). Additonally, Liu discloses methods of building interbeat interval series for the calculation of heart rate n-variability (step (d)) (pg. 3, para. (3); “RRnI”; “a new type of RRI.”), as well as calculating frequency domain features from heart rate n-variability (step j)(Table 2). Lastly, Liu discloses using heart rate n-variability in a prediction model (pg. 8, para. (1) ; “The final multivariable predictive model consisted of four vital signs, two traditional HRV parameters, and 15 novel HRnV parameters.”). However, Liu does not disclose that an output display or a microprocessor for performs these steps.
It would have been obvious to one of ordinary skill in the art before the effective filling date to combine the methods of Jensen (A) of measuring and calculating EEG and ECG metrics and inputting them into a prediction model with the methods of Jensen B where time domain features are also calculated and a cross-correlation is performed between the EEG and ECG signals. A cross-correlation is a known technique that could be applied to Jensen’s (A) methods to improve means of signal comparison between the EEG and ECG. Further, Jensen A is already comparing the signals to find mutual information, and using a cross-correlation would be an obvious technique to improve this method. Further, to use this cross-correlation method, one would have to obtain the time domain features of the EEG, which is a step Jensen A already performs for the ECG. Therefore, it would have been obvious to repeat this step to use in the cross-correlation calculation. Lastly, it would have been obvious to increase the number of inputs to 4 since Jensen already disclosed that the prediction model can use more than 3 inputs.
Page, in the same field of endeavor of monitoring patient health, calculating risk indexes, and sepsis prediction, discloses a system for monitoring patient health. Page discloses a microprocessor (para. [0062]; “The processor(s) may be any suitable processor, processing unit, or microprocessor, for example.”) for processing medical data (para. [0056]; “The processing and analysis of the time series streams of medical device data…”).
It would have been obvious to one of ordinary skill in the art before the effective filing date to combine the apparatus and steps disclosed by Jensen A and B and Liu with the implementation of a processor as disclosed in Page. Page demonstrates that a microprocessor can be used to process ECG signals and that the microprocessor can be used in a system for sepsis prediction. In suggesting the use of a processor in sepsis prediction (para. [0067]; “Furthermore, the stream processing module 106 coupled with inference engine 110 may perform predictions such as continuously predictive scoring, patient deterioration scoring, calculate risk indexes, identify early signs of trouble, sepsis prediction…) it is obvious that a processor should be configured to perform the steps.
Regarding claim 11, the combination of Jensen A and B, Liu, and Page disclose the apparatus according to claim 10 (see above). Further, Jensen A discloses wherein step a is characterized by a sensor consisting of 3 or more electrodes positioned on the forehead (17, 18 and 19) and 1 or more electrodes above the ear on one or both sides of the subject recording electroencephalogram from the insular cortex (20). (claim 34; The apparatus according to claim 33, characterized in that said sensor for measuring said EEG data consists of at least 3 electrodes, wherein said at least 3 electrodes are positioned on a forehead of said subject).
Given the broadest reasonable interpretation of “1 or more electrodes above the ear on one or both sides of the subject recording electroencephalogram from the insular cortex,” the electrodes of Jensen A would be within the meets and bounds of an electrode positioned above the ear since the forehead is above the ear.
It would have been obvious to one of ordinary skill in the art to combine the system of claim 10 as disclosed by the combination of Jensen A and B, Liu, and Page with the electrode placement of Jensen A and B. As disclosed by Jensen A, the forehead is a well-known location for EEG electrode placement that is known to be effective. Further, it would have been obvious to try placing electrodes above the ear since it is still above the forehead. There are a finite number of locations to place electrodes, and it would be reasonable to try placing them above the ear to obtain EEG data.
Regarding claim 12, the combination of Jensen A and B, Liu, and Page disclose the method according to claim 10 (see above). Jensen A discloses wherein said configured to build the interbeat interval series further comprises constructing series of the consecutive individual interbeat intervals in the case heart rate variability (para. [0035]). However, Jensen does not disclose the construction of series of intervals resulting from the sum of multiple consecutive interbeat intervals, with or without overlapping, in the case of heart rate n-variability.
Liu discloses the construction of series of intervals resulting from the sum of multiple consecutive interbeat intervals, with or without overlapping, in the case of heart rate n-variability (pg. 2, para. (3); “The proposed HRnV has two measures—HRnV and HRnVm. HRnV is derived from non-overlapping R-R intervals, while HRnVm is computed from overlapping R-R intervals.”)
It would have been obvious to one of ordinary skill in the art before the effective filing date to combine the apparatus configured for constructing series of intervals as disclosed in Jensen A and B, Liu, and Page with the series of overlapping or non-overlapping intervals for heart rate n-variability of Liu. The construction of intervals for heart rate n-variability is a known technique as disclosed by Liu, and using this technique in conjunction with the steps disclosed in Jensen is an obvious improvement of the previous method that only uses heart rate variability. In this instance, it is obvious to perform the same steps of constructing interval series for heart rate variability in constructing interval series for heart rate n-variability.
Regarding claim 13, the combination of Jensen A and B, Liu, and Page disclose the apparatus according to claim 10, wherein said configured to calculate the frequency domain features from the electroencephalogram (see above). Further, Jensen B discloses where this further comprises extracting frequency domain features from the electroencephalogram (3) such as the energy content in frequency bands of the electroencephalogram (para. [0062]; “The mutual information, Fokker-Planck drift and diffusion coefficients and cross correlation are calculated for the frequency bands of the EEG and ECG.) and the energy ratios across pairs of frequency bands of the electroencephalogram (para. [0069]; “A Fast Fourier Transform (FFT) is applied to the EEG and the energy in frequency bands are defined. From that ratios are calculated which are used as input to the classifier. The mutual information, Fokker-Planck drift and diffusion coefficients and cross correlation are calculated for the frequencies calculated of the EEG, EMG and ECG.”) Additionally, Liu discloses extracting frequency domain features from the electroencephalogram (3) such as the energy content in frequency bands of the electrocardiogram and the energy ratios across pairs of frequency bands of the electroencephalogram (see table 2 where Liu describes the extraction of HF, LF, voltage, and other energy and frequency contents from HR variability and HR n-variability calculations).
It would have been obvious for one of ordinary skill in the art before the effective filing date to combine the system of claim 10 as disclosed by the combination of Jensen A and B, Liu, and Page with the methods of extracting energy content and energy ratios from the EEG of Jensen B. Using the energy content and ratios is a known technique in the art as an input for predictive models, as demonstrated by Jensen B. Therefore, it would have been obvious to use this known input in a predictive model. In addition, it would have been obvious for one to extract frequency domain features from the EEG as in the case with Liu and combine the extraction with the system of claim 10. The extraction of frequency domain features for implementation in a predictive model are well known techniques in the art, as demonstrated by Liu.
Regarding claim 14, the combination of Jensen A and B, Liu, and Page disclose the apparatus according to claim 10, wherein said configured to calculate the frequency domain features from the electrocardiogram (see above). Further, Liu discloses extracting frequency domain features from the electrocardiogram (4) such as the energy content in frequency bands of the electrocardiogram and the energy ratios across pairs of frequency bands of the electrocardiogram (see table 2 where Liu describes the extraction of HF, LF, voltage, and other energy and frequency contents from HR variability and HR n-variability calculations).
It would have been obvious for one of ordinary skill in the art before the effective filing date to combine the system of claim 10 as disclosed by the combination of Jensen A and B, Liu, and Page with the methods of extracting energy content and energy ratios from the ECG of Liu. Using the energy content and ratios is a known technique in the art as an input for predictive models, as demonstrated by Liu. Therefore, it would have been obvious to use this known input in a predictive model. In addition, it would have been obvious for one to extract frequency domain features from the EEG as in the case with Liu and combine the extraction with the system of claim 10. The extraction of frequency domain features for implementation in a predictive model are well known techniques in the art, as demonstrated by Liu.
Regarding claim 15, the combination of Jensen A and B, Liu, and Page disclose the apparatus according to claim 10, wherein said configured to calculate time domain features from the heart rate variability and heart rate n-variability (see above). Further, Liu discloses where this further comprises extracting time domain features from the series of intervals considered in both heart rate variability and heart rate n-variability such as the root mean square differences between successive intervals (RMSSD), (Table 2) the standard deviation of the differences between successive intervals (SDSD) (Table 2), the percentage of successive intervals differing by more than 50ms (pNN50) (Table 2), the standard deviation of the intervals typically computed over a 24-hour period (SDNN) (Table 2), or the standard deviation of the average intervals computed over short periods, typically 5 minutes (SDANN)(Table 2).
It would have been obvious to combine the apparatus disclosed by the combination of Jensen A and B, Liu, and Page of claim 10 with the defined extraction of time domain features of Liu. The extracted features are known elements of time domain features in both heart rate variability and heart rate n-variability, as demonstrated by Liu. Further, it would have been obvious to use these extracted features in a predictive model for sepsis, as also in the case of Liu.
Regarding claim 16, the combination of Jensen A and B, Liu, and Page disclose the apparatus according to claim 10, wherein said configured to calculate frequency domain features from the heart rate variability and heart rate n-variability (see above). Liu discloses where this further comprises extracting frequency domain features from the series of intervals considered in both heart rate variability and heart rate n-variability such as the power below 0.04Hz corresponding to the very low frequency range (VLF)(table 2), the power between 0.04Hz and 0.15Hz corresponding to the low frequency range (LF)(table 2), the power between 0.15Hz and 0.4Hz corresponding to the high frequency range (HF)(table 2), the normalized power in the low frequency range (nLF) (table 2) defined as nLF = LF/(LF+HF)*100, the normalized power in the high frequency range (nHF)(table 2) defined as nHF = HF/(LF+HF)*100, or the ratio of the power in the low frequency range and the power in the high frequency range (LF/HF)(table 2). However, Liu does not specifically define the VFL, LF, and HF frequency ranges, or the normalized power for HF and LF.
Jensen A discloses the power between 0.04Hz and 0.15Hz corresponding to the low frequency range (LF)(Table 1; “Power in low frequency range (0 – 0.14Hz)”), the power between 0.15Hz and 0.4Hz corresponding to the high frequency range (HF)(table 1; “HF Power in high frequency range (0.15-0.4 Hz).”), the normalized power in the high frequency range (nHF) defined as nHF = HF/(LF+HF)*100 (table 2; “HF power in normalized units, HFn = HF/(LF + HF) * 100 (n.u).”).
It would have been obvious to combine the methods disclosed by the combination of Jensen A and B and Liu of claim 1 with the defined extraction of frequency domain features of Liu. The extracted features are known elements of frequency domain features in both heart rate variability and heart rate n-variability, as demonstrated by Liu. Further, it would have been obvious to use these extracted features in a predictive model for sepsis as in the case of Liu. Additionally, it would have been obvious to one having ordinary skill in the art at the time the invention was made to optimize and arrive at an LF of 0.04-0.14 Hz, as well as optimizing inputs by creating a VFL category that is 0-0.04Hz, recognizing that frequency is directly correlated to power output. Further, these are arbitrary categories in which power output is characterized. It has been held that where the general conditions of a claim are disclosed in the prior art, discovering the optimum or workable ranges involves only routine skill in the art. In re Aller, 105 USPQ 233. Please note that in the instant application, the Applicant has not disclosed any criticality for the claimed limitation. Lastly, it would have been obvious to perform the same normalization of HF power as performed in LF power since the equation is a known technique, as disclosed by Jensen A, in normalizing a frequency. Applying this would improve the apparatus by providing the predictive variables more input, and therefore, improving the references it is able to use in predicting sepsis.
Regarding claim 17, the combination of Jensen A and B, Liu, and Page disclose the apparatus according to claim 10, wherein said configured to calculate nonlinear features from the heart rate variability and heart rate n-variability (see above). Liu discloses where this further comprises extracting nonlinear features from the series of intervals considered in both heart rate variability and heart rate n-variability such as the approximate entropy (ApEn) (table 2), the sample entropy (SampEn) (table 2) or the coefficients α 1 and α 2 provided by the detrended fluctuation analysis (DFA). )(Both are included in table 2; Table 2 includes all of the non-linear features for both heart rate variability and heart rate n-variability).
It would have been obvious to combine the apparatus of claim 10 disclosed by the combination of Jensen A and B, Liu, and Page with the extraction of nonlinear features of Liu. The extracted features are known elements in both heart rate variability and heart rate n-variability, as demonstrated by Liu. Further, it would have been obvious to use these extracted features in a predictive model for sepsis, as in the case of Liu.
Regarding claim 18, the combination of Jensen A and B, Liu, and Page disclose the apparatus according to claim 10, wherein said configured to calculate the cross-correlation and the mutual information between the electroencephalogram and the electrocardiogram, the heart rate variability and the heart rate n-variability (see above). Further, Jensen B discloses where this further comprises by calculating features derived from the cross-correlation and mutual information functions between the energy content and energy ratios of the electroencephalogram (3) and the energy content and energy ratios of the electrocardiogram (4) (para. [0069]; “A Fast Fourier Transform (FFT) is applied to the EEG and the energy in frequency bands are defined. From that ratios are calculated which are used as input to the classifier. The mutual information, Fokker-Planck drift and diffusion coefficients and cross correlation are calculated for the frequencies calculated of the EEG, EMG and ECG”). Additionally, Liu discloses where calculating features from the series of intervals considered in both heart rate variability and heart rate n-variability (table 2 describes DFA coefficients derived from heart rate variability and heart rate n variability).
It would have been obvious to one of ordinary skill in the art to combine the apparatus of claim 10 as disclosed in the combination of Jensen A and B, Liu, and Page to include calculating energy content and ratio features derived from the EEG, ECG, heart rate variability, and heart rate n-variability as disclosed in Liu and Jensen B. Performing a cross-correlation, as disclosed by Jensen, is a well-known technique in the art that further improves the method of comparing signals by analyzing the mutual information shared between them. Further, it would have been obvious to include the well-known technique of heart rate n-variability in this calculation and comparing the features obtained with the heart rate variability features. Doing so would improve the method of calculating input for a predictive model for sepsis, as disclosed in Liu.
Regarding claim 19, the combination of Jensen A and B, Liu, and Page disclose the apparatus according to claim 10, wherein said configured to use a prediction model further (see above). Further, Jensen B discloses where a prediction model which can be either a linear regression, a logistic regression, a fuzzy logic classifier, a neural network, a hybrid between a fuzzy logic system and a neural network such as an adaptive neuro fuzzy inference system, or any other prediction model (para. [0060]; “The parameters extracted from EEG, EMG, and HRV are all used as input to the classifier (13) which could be either a linear regression, a logistic regression, a fuzzy logic classifier, a neural network or a hybrid between a fuzzy logic system and a neural network such as an Adaptive Neuro Fuzzy Inference System (ANFIS)”).
It would have been obvious to one of ordinary skill in the art before the effective filing date to include the predictive model options, as disclosed by Jensen B, with the apparatus of claim 10. It would have been obvious to try one of the listed predictive models of claim 8 since there are a finite number of predictive models available. Further, Jensen B discloses the same optional predictive models, meaning they are well known in the art. Jensen uses the predictive model to predict an index from EEG and ECG data as well, meaning these predictive models have been known to produce a predictable solution in attempting to output an index from EEG and ECG data.
Regarding claim 20, the combination of Jensen A and B, Liu, and Page disclose the apparatus according to claim 11 (see above). Further, Page discloses wherein the apparatus comprises a microprocessor (para. [0062]; “The processor(s) may be any suitable processor, processing unit, or microprocessor, for example.”) configured to present an output to a display (para. [0058]; “display (e.g. screen or monitor)”), among others, may be any of the following: one or several EEG signals, one or several ECG signals, the value of the level of sepsis, the value of the heart rate (HR) (para. [0108]; “The in-room GUI 2100 includes a plurality of patient monitoring tiles, such as patient monitoring tile 2114 (which is displaying patient heart rate both as a representative ECG waveform and as a most-recently determined value.”), the value of the burst suppression ratio (BSR), the value of the impedance of the electrodes (IMP), the value of a signal quality index (SQI), the value of the level of the battery (BAT) or the trend of any of the calculated indices over time.
It would have been obvious to one of ordinary skill in the art before the effective filing date to combine the apparatus of claim 11, as disclosed by Jensen A and B, Liu, and Page with the processor and display to display ECG signals and heart rate as disclosed by Page. A microprocessor is a well-known computer component for ECG processing as it is used in Page. Additionally, including a display is an obvious improvement that would allow the person performing the methods of claim one to easily visualize the data. Lastly, including the following outputs on the display is a well-known technique for ECG data visualization, as disclosed by Page. Applying these well-known techniques would have resulted in obvious improvements of signal processing and data visualization.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to OWEN LEWIS MARSH whose telephone number is (571)272-8584. The examiner can normally be reached 7:30am – 5pm (M-Th) and 8am – 5pm (F).
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Jennifer McDonald can be reached at (571) 270-3061. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/OWEN LEWIS MARSH/Examiner, Art Unit 3796
/Jennifer Pitrak McDonald/Supervisory Patent Examiner, Art Unit 3796