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(s) 4, 7, 10, and 18 is/are objected to because of the following informalities:
The Examiner notes that claim 4 recites several instances of abbreviated or shortened terms [“HR”, “fSys”, “Dia”, “Sys”, “dP”, and “dt” in lines 7-8] that are not previously defined or specifically associated with any of the previously recited parameters. The first instance of each abbreviated or shortened term should be accompanied by corresponding language to define the abbreviated/shortened term. Claim 18 [lines 7-8] is similarly objected to mutatis mutandis.
Claim 7 should read “when systolic mean arterial pressure (MAP) is reached” [line 3], as the Examiner notes that claims 7 and 10 are not dependent from claim 4, which does define “MAP”. Claim 10 [line 4] is similarly objected to mutatis mutandis.
Appropriate correction is required.
Claim Interpretation
Examiner Notes: currently, NO limitation invokes interpretation under § 112(f).
Claim Analysis - 35 USC § 112
Examiner’s Note Regarding Machine Learning: the claimed predictive computational model of claim(s) 1, 5-6, 9-12, 15, and 19-20 was considered under § 112(a), wherein the Examiner notes that the disclosure of exemplary various computational models [To screen for or predict a probability of sepsis, a computational model can be trained on hemodynamic data that was collected from a cohort of patients having a known diagnosis of sepsis. The hemodynamic data of each patient can be associated with the patient's sepsis diagnosis to train the model. Various computational models can be utilized, including (but not limited to) regression-based or classification-based models. Regression-based models include (but are not limited to) LASSO regression, ridge regression, k-nearest neighbors, elastic net, least angle regression (LAR), and random forest regression. Classification-based models include (but are not limited to) logistic regression, support vector machines (SVMs), decision trees, random forests, and naïve Bayes. In some implementations, the model is regularized. In some implementations, the model can be ensembled from multiple models from one or more model types listed above (Applicant’s Specification ¶0058)] of the Applicant’s Specification is considered to provide sufficient written description support for the predictive computational model predictive computational model as presently claimed for one of ordinary skill in the art to understand that the Applicant possessed the instant invention at the time of filing.
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.
Claim(s) 1-20 is/are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception without significantly more. Each claim has been analyzed to determine whether it is directed to any judicial exceptions.
Representative claim(s) 1 [representing all independent claims] recite(s):
A computational method for screening for sepsis, comprising:
receiving waveform data corresponding to an arterial blood pressure, or a signal proportional to, or derived from, the arterial blood pressure, from a sensor applied to a patient;
extracting a set of hemodynamic data features from the waveform data; and
entering the set of extracted hemodynamic data features into a predictive computational model to yield a screening score of sepsis, wherein the predictive computational model has been trained to screen for sepsis utilizing the set of extracted hemodynamic data features.
(Emphasis added: abstract idea, additional element)
Step 2A Prong 1
Representative claim(s) 1 recites the following abstract ideas, which may be performed in the mind or by hand with the assistance of pen and paper:
“receiving waveform data corresponding to an arterial blood pressure, or a signal proportional to, or derived from, the arterial blood pressure, from a sensor applied to a patient” – may be performed by merely observing at least a limited amount of known or previously collected data; wherein the Examiner notes that the identified limitation as presently written is not considered to positively recite a sensor to define any step of measuring waveform data or utilizing a sensor applied to a patient as a form of data gathering, such that the recitation that the data is “from a sensor applied to a patient” is merely considered to limit the type of data or where the data came from
“extracting a set of hemodynamic data features from the waveform data” – may be performed by merely drawing mental conclusions on at least a limited amount of known or previously collected data based on known or derived mathematical formulas or relationships
If a claim, under BRI, covers performance of the limitations in the mind but for the mere recitation of extra-solutionary activity (and otherwise generic computer elements) then the claim falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea under Step 2A Prong 1 of the Mayo framework as set forth in the 2019 PEG.
No limitations are provided that would force the complexity of any of the identified evaluation steps to be non-performable by pen-and-paper practice.
Alternatively or additionally, these steps describe the concept of using implicit mathematical formula(s) [i.e., “extracting a set of hemodynamic data features from the waveform data”] to derive a conclusion based on input of data, which corresponds to concepts identified as abstract ideas by the courts [Diamond v. Diehr. 450 U.S. 175, 209 U.S.P.Q. 1 (1981), Parker v. Flook. 437 U.S. 584, 19 U.S.P.Q. 193 (1978), and In re Grams. 888 F.2d 835, 12 U.S.P.Q.2d 1824 (Fed. Cir. 1989)]. The concept of the recited limitations identified as mathematical concepts above is not meaningfully different than those mathematical concepts found by the courts to be abstract ideas.
The dependent claims merely include limitations that either further define the abstract idea [e.g. limitations relating to the data gathered or particular steps which are entirely embodied in the mental process] and amount to no more than generally linking the use of the abstract idea to a particular technological environment or field of use because they are merely incidental or token additions to the claims that do not alter or affect how the process steps are performed.
Thus, these concepts are similar to court decisions of abstract ideas of itself: collecting, displaying, and manipulating data [Int. Ventures v. Cap One Financial], collecting information, analyzing it, and displaying certain results of the collection and analysis [Electric Power Group], collection, storage, and recognition of data [Smart Systems Innovations].
Step 2A Prong 2
The judicial exception is not integrated into a practical application.
Representative claim 1 only recites additional elements of extra-solutionary activity – in particular, extra-solution activity [generic computer function; and for the sake of compact prosecution, the recitation of “a sensor applied to a patient” is interpreted to refer to pre-solution data gathering] – without further sufficient detail that would tie the abstract portions of the claim into a specific practical application (2019 PEG p. 55 – the instant claim, for example does not tie into a particular machine, a sufficiently particular form of data or signal collection – via the claimed extra-solution activity identified above, or a sufficiently particular form of display or computing architecture/structure).
Dependent claim(s) 3-4, 7-8, 13, and 17-18 merely add detail to the abstract portions of the claim but do not otherwise encompass any additional elements which tie the claim(s) into a particular application/integration [the dependent claim(s) recite generic ‘units’ or ‘steps’ which encompass mere computer instructions to carry out an otherwise wholly abstract idea].
Dependent claim(s) 2 and 16 encounter substantially the same issues as the independent claim(s) from which they depend in that they encompass further generic extra-solutionary activity [generic data gathering] and/or generic computer elements [storage, memory per se].
Accordingly, the claim(s) are not integrated into a practical application under Step 2A Prong 2.
Step 2B
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception.
Independent claims 1 and 15 as individual wholes fail to amount to significantly more than the judicial exception at Step 2B. As discussed above with respect to integration of the abstract idea into a practical application, the additional elements of extra-solutionary activity [i.e., generic computer function, pre-solution data gathering] and generic computer elements cannot amount to significantly more than an abstract idea [MPEP § 2106.05(f)] and is further considered to merely implement an abstract idea on a generic computer [MPEP § 2106.05(d)(II) establishes computer-based elements which are considered to be well understood, routine, and conventional when recited at a high level of generality].
For the independent claim portions and dependent claims which provide additional elements of extra-solutionary data gathering, MPEP § 2106.05(g) establishes that mere data gathering for determining a result does not amount to significantly more. The extra-solutionary activity of processor steps [acquiring, transmitting signals, etc.] as presently recited, cannot provide an inventive concept which amounts to significantly more than the recited abstract idea.
For the independent claims as well as the dependent claims merely reciting generic computer elements and functions [the methods of claims 1 and 15 are recited as being “computational”, which is considered to refer to a computer at a high level of generality and corresponding functions therein], MPEP § 2106.05(d)(II) establishes computer-based elements which are considered to be well understood, routine, and conventional when recited at a high level of generality.
Accordingly, the generic computer elements and corresponding functions, as presently limited, cannot provide an inventive concept since they fall under a generic structure and/or function that does not add a meaningful additional feature to the judicial exception(s) of the claim(s).
Claim 1 recites “a sensor applied to a patient”, which is not considered to be a positive recitation of a sensor or application of the sensor to the patient, but for the sake of compact prosecution is further analyzed as if the sensor were to be positively recited, wherein claim 2 recites a step of “sensing, using the sensor, the arterial blood pressure”, and wherein claim 3 recites “wherein the sensor is an intra-arterial catheter and a disposable pressure transducer, a pressurized finger cuff and light sensor, or an applanation tonometer”; claim 15 recites similar language to claim 1 regarding a sensor applied to a patient that is similar interpreted mutatis mutandis. Such a “sensor” is considered well-understood, routine, and conventional, as known by at least:
Applicant’s disclosure is not particular regarding the particular structure of the generically claimed “sensor”, and recites the “sensor” at a high level of generality [Accordingly, blood pressure can be measured via an intra-arterial catheter (e.g., pressure catheter within an artery) with a disposable pressure transducer, via a pressurized finger cuff and light sensor (e.g., volume clamp method), via applanation tonometry, or any other means that yields an arterial pressure waveform or a signal proportional to, or derived from, the arterial blood pressure (Applicant’s Specification ¶0055); Sensors include (but are not limited to) intra-arterial catheter, a disposable pressure transducer, a pressurized finger cuff and light sensor, and an applanation tonometer (¶0071); The sensor 118 can be a noninvasive or an invasive pressure sensor. Accordingly, the sensor 118 can be an intra-arterial catheter (e.g., pressure catheter within an artery) with a disposable pressure transducer, a pressurized finger cuff and light sensor (e.g., volume clamp method), an applanation tonometer, or any other pressure sensor that yields an arterial pressure waveform (¶0074)]. This lack of disclosure is acceptable under 35 U.S.C. 112(a) since this hardware performs non-specialized functions known by those of ordinary skill in the medical technology arts. Thus, Applicant's specification essentially admits that this hardware is conventional and performs well understood, routine and conventional activities in the field of blood pressure monitoring. In other words, Applicant’s specification demonstrates the well-understood, routine, conventional nature of the above-identified additional element because it describes such an additional element in a manner that indicates that the additional element is sufficiently well-known that the specification does not need to describe the particulars of such additional elements to satisfy 35 U.S.C. 112(a) [see Berkheimer memo from April 19, 2018, Page 3, (III)(A)(1), not attached]. Adding hardware that performs “well understood, routine, conventional activit[ies]’ previously known to the industry” will not make claims patent-eligible [TLI Communications].
Kaspari (US-5533511-A) [The first set of data is the actual blood pressure obtained, for example, using conventional intra-arterial catheters and associated pressure transducers. These catheters are routinely inserted during many types of surgeries, usually in the patient's radial artery. If sufficient data cannot be collected using intra-arterial catheters, intermittent occlusive cuff devices may be used, provided the values obtained can be correlated with the appropriate waveshape. The signal obtained from the pressure transducer is digitized and stored in a data acquisition system. This becomes the reference data, i.e., the data that serves as the absolute, true value of the individual's blood pressure (Kaspari Col 12:16-28)]
Westerhof (US-20190104991-A1) [FIG. 2 is an example of a conventional finger cuff. With reference to FIG. 2, a conventional finger cuff 300 may be formed from a flexible material with a Velcro clamping system (Westerhof ¶0019); Further, finger cuff 300 may include a bladder 340 and an LED-PD pair 335a-b mounted on the interior of the finger cuff 300… The bladder 340 and LED-PD pair 335a-b may be coupled to tube or cable 360 through a connector, which may be attached to finger cuff 300, to provide pneumatic pressure to the bladder 340, and to provide power to and receive data from the LED-PD pair 335a-b. The LED-PD pair 335a-b may be used to perform measurements of a pleth signal to aid in measuring the patient's blood pressure (Westerhof ¶0020)]
Morris (US-20150196209-A1) [The risk factor evaluation component 116 can be configured to derive a pulse pressure, a blood pressure (with calibration), an augmentation index, and/or a systolic ejection time of the user 104 via the pulse wave analysis. In contrast to the chair 102 enabling the pulse wave analysis of the user 104 to be performed, conventional approaches oftentimes perform a pulse wave analysis using a pressure sensor placed in (e.g., using a catheter) or above (e.g., using an applanation tonometer) an artery (Morris ¶0032)]
Claim 1 recites “entering the set of extracted hemodynamic data features into a predictive computational model to yield a screening score of sepsis, wherein the predictive computational model has been trained to screen for sepsis utilizing the set of extracted hemodynamic data features”; claim 5 recites “entering patient clinical information into the model”, wherein claim 6 further limits the type of patient clinical information; claim 9 recites “wherein the predictive computational model utilizes an equation to yield the screening score of sepsis”, wherein claims 10-11 recite particular mathematical equations utilized by the model; claim 12 recites “wherein the predictive computational model is a regression-based model, a classification-based model or an ensembled model”; claim 15 recites “entering the set of extracted hemodynamic data features into a predictive computational model to yield a probability score of sepsis, wherein the predictive computational model has been trained to predict for sepsis utilizing the set of extracted hemodynamic data features”; claim 19 recites “entering patient clinical information into the model”, wherein claim 20 further limits the type of patient clinical information. Such a “predictive computational model” for mere input and output is considered well-understood, routine, and conventional, as known by at least:
Hu (“Intelligent Sensor Networks”, NPL attached) [In supervised learning, the learner is provided with labeled input data. This data contains a sequence of input/output pairs of the form xi, yi, where xi is a possible input and yi is the correctly labeled output associated with it. The aim of the learner in supervised learning is to learn the mapping from inputs to outputs. The learning program is expected to learn a function f that accounts for the input/output pairs seen so far, f (xi) = yi, for all i. This function f is called a classifier if the output is discrete and a regression function if the output is continuous. The job of the classifier/regression function is to correctly predict the outputs of inputs it has not seen before (Hu, Page 5)]
Huang (“Kernel Based Algorithms for Mining Huge Data Sets”, NPL attached) [In supervised learning, the learner is provided with labeled input data. This data contains a sequence of input/output pairs of the form xi, yi, where xi is a possible input and yi is the correctly labeled output associated with it. The aim of the learner in supervised learning is to learn the mapping from inputs to outputs. The learning program is expected to learn a function f that accounts for the input/output pairs seen so far, f (xi) = yi, for all i. This function f is called a classifier if the output is discrete and a regression function if the output is continuous. The job of the classifier/regression function is to correctly predict the outputs of inputs it has not seen before (Huang, Page 1)]
Mitchell (“The Discipline of Machine Learning”, NPL attached) [For example, we now have a variety of algorithms for supervised learning of classification and regression functions; that is, for learning some initially unknown function f : X [Calibri font/0xE0] Y given a set of labeled training examples {xi; yi} of inputs xi and outputs yi = f(xi) (Mitchell, Pages 3-4)]
Examiner’s Note Regarding Particular Treatment or Prophylaxis: Claim(s) 13-14 recite subject matter regarding “further assessing the patient for sepsis complications” [claim 13] and “monitoring the patient for sepsis complications for a certain period of time” [claim 14], which the Examiner notes is not considered to be a particular treatment or prophylaxis, as none of the identified claims positively recite or include language that is considered to be a particular treatment or prophylaxis as an additional element to integrate the judicial exception into a practical application or allow the identified claims to amount to significantly more than the judicial exception [MPEP § 2106.04(d)(2)].
Accordingly, the claim(s) as whole(s) fail amount to significantly more than the judicial exception under Step 2B.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claim(s) 1-6, 9, and 12-20 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Newberry (US-20200253562-A1, cited by Applicant).
Regarding claim 1, Newberry teaches
A computational method for screening for sepsis [One or more types of neural networks (a.k.a., machine learning algorithms) may be implemented herein to diagnose an infection (such as sepsis, influenza, COVID-19, pneumonia, etc.) in a patient and/or determine a severity of the infection in the patient (Newberry ¶0295)], comprising:
receiving waveform data corresponding to an arterial blood pressure, or a signal proportional to, or derived from, the arterial blood pressure, from a sensor applied to a patient [the biosensor includes an optical sensor photoplethysmography (PPG) circuit configured to transmit light at a plurality of wavelengths directed at skin tissue of a patient (Newberry ¶0118); For example, neural networks may be used to analyze data derived from PPG signals (Newberry ¶0296); The biosensor 100 may also measure the amplitude of the pressure pulse wave as an estimation of blood pressure. In another embodiment, the neural network processing device 4000 may estimate a systolic blood pressure from PPG signals (Newberry ¶0318); The biosensor 100 may also monitor heart rate, oxygen saturation and estimate blood pressure. These and other parameters may be obtained using one or more PPG signals. The PPG input data may include the PPG signals, and/or one or more parameters derived from the PPG signals (Newberry ¶0325); The biosensor 100 obtains a plurality of PPG signals at a plurality of wavelengths from a patient at 4212. As described with respect to FIG. 42A, the biosensor 100 may determine a respiratory rate and estimation of systolic and diastolic blood pressure from one or more of the plurality of PPG signals. The mean arterial pressure (MAP) may be determined from the SBP and DBP (Newberry ¶0342)];
extracting a set of hemodynamic data features from the waveform data [Newberry ¶¶0318, 0325, 0342]; and
entering the set of extracted hemodynamic data features into a predictive computational model to yield a screening score of sepsis, wherein the predictive computational model has been trained to screen for sepsis utilizing the set of extracted hemodynamic data features [The PPG input data may include the PPG signals, and/or one or more parameters derived from the PPG signals (Newberry ¶0325); The plurality of PPG and health parameters of the patient are processed by a processing device executing a neural network (aka machine learning algorithm) at 4112. The processing device executes the machine learning algorithm or neural network techniques to determine health data. The health data includes a diagnosis of whether an infection is present in the patient. The diagnosis may also include a type of infection, such as sepsis (Newberry ¶0327)].
Regarding claim 2, Newberry teaches
The computational method of claim 1 further comprising: sensing, using the sensor, the arterial blood pressure [Newberry ¶¶0318, 0342].
Regarding claim 3, Newberry teaches
The computational method of claim 1, wherein the sensor is an intra-arterial catheter and a disposable pressure transducer, a pressurized finger cuff and light sensor [FIG. 6 illustrates a schematic block diagram illustrating an embodiment of the PPG circuit 110 in more detail. The PPG circuit 110 includes a light source 620 configured to emit a plurality of wavelengths of light across various spectrums (Newberry ¶0136); The PPG circuit 110 further includes one or more photodetector circuits 630a-n. For example, a first photodetector circuit 630 may be configured to detect visible light and the second photodetector circuit 630 may be configured to detect IR light. Alternatively, both photodetectors 630a-n may be configured to detect light across multiple spectrums and the signals obtained from the photodetectors are added or averaged (Newberry ¶0138); FIG. 44 illustrates a perspective view of the biosensor 100 positioned on a finger of a patient. The biosensor 100 includes the finger boot 4302 configured to securely hold the biosensor 100 onto the finger. The finger boot 4302 may include rubber or other pliable material that may stretch around and exert a pressure on the finger to hold it securely (Newberry ¶0351, Fig. 44)], or an applanation tonometer.
Regarding claim 4, Newberry teaches
The computational method of claim 1, wherein the set of extracted hemodynamic features comprises at least one of: heart rate [Newberry ¶0325], respiration rate [Newberry ¶0325], cardiac output, stroke volume [Specific measurements or the PPG signal may be determined and input as parameters or compared, e.g. a time between systolic and diastolic points of the PPG signal, e.g. a stroke length, stroke period, amplitude, etc. (Newberry ¶0316)], stroke volume variation [Newberry ¶0316, wherein a comparison between stroke volumes is considered to read on variation], vascular tone, contractility, afterload, systemic vascular resistance, systolic pressure [Newberry ¶0342], diastolic pressure [Newberry ¶0342], mean arterial pressure (MAP) [Newberry ¶0342], kurtosis of pressure distribution, left ventricular ejection time, time from when systolic MAP is reached to the dicrotic notch, sample entropy of the time when systolic MAP is reached, entropy of the standard deviation of decay phase
H
R
f
S
y
s
,
D
i
a
M
A
P
,
S
y
s
-
D
i
a
M
A
P
,
M
A
P
-
D
i
a
S
y
s
-
D
i
a
, or
d
P
d
t
.
Regarding claim 5, Newberry teaches
The computational method of any one of claim 1, further comprising entering patient clinical information into the model [In an embodiment, additional health parameters or patient data is obtained at 4110. The patient data may include one or more of: age, weight, body mass index, temperature, SOFA or qSOFA score, mean arterial pressure (MAP), pre-existing medical conditions, trauma events, mental conditions, injuries, demographic data, physical examinations, laboratory tests, diagnosis, treatment procedures, medications, radiology examinations, historic pathology, medical history, surgeries, etc. (Newberry ¶0326)].
Regarding claim 6, Newberry teaches
The computational method of claim 5, wherein the patient clinical information comprises at least one of: patient demographics, patient vital signs, and patient laboratory results [Newberry ¶0326].
Regarding claim 9, Newberry teaches
The computational method of claim 1, wherein the predictive computational model utilizes an equation to yield the screening score of sepsis [In an embodiment, one or more types of artificial intelligence or neural network processing models may be implemented by the processing device 4000 to determine an output 4006 including health data 4008, 4010, 4012 from one or more of the input parameters 4004. For example, the processing device 4000 may implement a regression model or classifier type model. A regression module neural network may be trained using one or more learning vectors with similar types of input parameters and known outputs as described further hereinabove. A classifier neural network may be applied to the one or more input parameters 4004 to classify a patient as having an infection or no infection (Newberry ¶0322), wherein linear regression or a classifier is considered to read on the use of an equation based on the broadest reasonable interpretation of an equation].
Regarding claim 12, Newberry teaches
The computational method of any one of claim 1, wherein the predictive computational model is a regression-based model, a classification-based model [Newberry ¶0322] or an ensembled model.
Regarding claim 13, Newberry teaches
The computational method of any one of claim 1, wherein the screening score of sepsis indicates a risk of developing sepsis [In one or more embodiments herein, an early warning system and method is described for early detection or prediction of sepsis… The biosensor includes a visible or audible indicator that signals detection of sepsis or a risk of sepsis (Newberry ¶0117); The health data may also include a confidence factor in the diagnosis (Newberry ¶0327)]; the method further comprising:
further assessing the patient for sepsis complications [The health data may further include a severity level of the illness. Alarms or warnings may be issued based on the health data. Recommended further screening or tests may be included as well (Newberry ¶0327)].
Regarding claim 14, Newberry teaches
The computational method of any one of claims 1 to 13, wherein the screening score of sepsis indicates a risk of developing sepsis [Newberry ¶¶0117, 0327]; the method further comprising:
monitoring the patient for sepsis complications for a certain period of time [Newberry ¶0327].
Regarding claim 15, Newberry teaches
A computational method for predicting a probability of a patient experiencing sepsis [One or more types of neural networks (a.k.a., machine learning algorithms) may be implemented herein to diagnose an infection (such as sepsis, influenza, COVID-19, pneumonia, etc.) in a patient and/or determine a severity of the infection in the patient (Newberry ¶0295)], comprising:
receiving waveform data corresponding to an arterial blood pressure, or proportional to, or derived from, the arterial blood pressure, from a sensor applied to a patient [the biosensor includes an optical sensor photoplethysmography (PPG) circuit configured to transmit light at a plurality of wavelengths directed at skin tissue of a patient (Newberry ¶0118); For example, neural networks may be used to analyze data derived from PPG signals (Newberry ¶0296); The biosensor 100 may also measure the amplitude of the pressure pulse wave as an estimation of blood pressure. In another embodiment, the neural network processing device 4000 may estimate a systolic blood pressure from PPG signals (Newberry ¶0318); The biosensor 100 may also monitor heart rate, oxygen saturation and estimate blood pressure. These and other parameters may be obtained using one or more PPG signals. The PPG input data may include the PPG signals, and/or one or more parameters derived from the PPG signals (Newberry ¶0325); The biosensor 100 obtains a plurality of PPG signals at a plurality of wavelengths from a patient at 4212. As described with respect to FIG. 42A, the biosensor 100 may determine a respiratory rate and estimation of systolic and diastolic blood pressure from one or more of the plurality of PPG signals. The mean arterial pressure (MAP) may be determined from the SBP and DBP (Newberry ¶0342)];
extracting a set of hemodynamic data features from the waveform data [Newberry ¶¶0318, 0325, 0342]; and
entering the set of extracted hemodynamic data features into a predictive computational model to yield a probability score of sepsis, wherein the predictive computational model has been trained to predict for sepsis utilizing the set of extracted hemodynamic data features [In one or more embodiments herein, an early warning system and method is described for early detection or prediction of sepsis… The biosensor includes a visible or audible indicator that signals detection of sepsis or a risk of sepsis (Newberry ¶0117); The PPG input data may include the PPG signals, and/or one or more parameters derived from the PPG signals (Newberry ¶0325); The plurality of PPG and health parameters of the patient are processed by a processing device executing a neural network (aka machine learning algorithm) at 4112. The processing device executes the machine learning algorithm or neural network techniques to determine health data. The health data includes a diagnosis of whether an infection is present in the patient. The diagnosis may also include a type of infection, such as sepsis… The health data may also include a confidence factor in the diagnosis (Newberry ¶0327)].
Regarding claim 16, Newberry teaches
The computational method of claim 15 further comprising:
sensing, using the sensor, the arterial blood pressure [Newberry ¶¶0318, 0342].
Regarding claim 17, Newberry teaches
The computational method of claim 15, wherein the sensor is an intra-arterial catheter and a disposable pressure transducer, a pressurized finger cuff and light sensor [Newberry ¶¶0136, 0138, 0351, Fig. 44], or an applanation tonometer.
Regarding claim 18, Newberry teaches
The computational method of claim 15, wherein the set of extracted hemodynamic features comprises at least one of: heart rate [Newberry ¶0325], respiration rate [Newberry ¶0325], cardiac output, stroke volume [Newberry ¶0316], stroke volume variation [Newberry ¶0316, wherein a comparison between stroke volumes is considered to read on variation], vascular tone, contractility, afterload, systemic vascular resistance, systolic pressure [Newberry ¶0342], diastolic pressure [Newberry ¶0342], mean arterial pressure (MAP) [Newberry ¶0342], kurtosis of pressure distribution, left ventricular ejection time, time from when systolic MAP is reached to the dicrotic notch, sample entropy of the time when systolic MAP is reached, entropy of inter-beat interval, entropy of the standard deviation of decay phase
H
R
f
S
y
s
,
D
i
a
M
A
P
,
S
y
s
-
D
i
a
M
A
P
,
M
A
P
-
D
i
a
S
y
s
-
D
i
a
, or
d
P
d
t
.
Regarding claim 19, Newberry teaches
The computational method of claim 15, further comprising entering patient clinical information into the model [Newberry ¶0326].
Regarding claim 20, Newberry teaches
The computational method of claim 19, wherein the patient clinical information comprises at least one of: patient demographics, patient vital signs, and patient laboratory results [Newberry ¶0326].
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.
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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claim(s) 7 is/are rejected under 35 U.S.C. 103 as being unpatentable over Newberry, as applied to claim 1 above, in further view of Song et al. (“A Predictive Model Based on Machine Learning for the Early Detection of Late-Onset Neonatal Sepsis: Development and Observational Study”, NPL attached), hereinafter Song, and Mollura et al. (“Assessment of Sepsis in the ICU by Linear and Complex Characterization of Cardiovascular Dynamics”, NPL attached), hereinafter Mollura.
Regarding claim 7, Garcia teaches
The computational method of claim 1, wherein the set of extracted features comprises heart rate [Newberry ¶0325].
However, Newberry fails to explicitly disclose wherein the set of extracted features also comprises kurtosis of pressure distribution and sample entropy of the time when systolic MAP is reached.
Song discloses methods for using a prediction model to detect sepsis, wherein Song discloses that relevant parameters in detecting the onset of sepsis [This study showed that when the biosignals recorded in EMR are used to select and learn features based on the presented algorithm, it is possible to produce a model that can predict LONS 48 hours earlier. Our model also showed a higher or similar performance to the high-resolution model of previous studies (Song p. 12)] includes: heart rate [Song p. 3, Tables 4-5 on p. 10-11], and kurtosis and entropy of diastolic, systolic, and mean blood pressure [Song Table 4 on p. 10].
Mollura discloses methods for identifying septic patients, wherein Mollura discloses that relevant parameters in detecting the onset of sepsis includes: sample entropy of systolic arterial pressure [Sample entropy measures computed on pressure time series (SAP_SampEn and DAP_SampEn) result statistically significant (p<0.01 and p<0.05) when comparing the two populations, showing both odds<1 for unitary increase as well as cross-sample entropy from RR and SAP series (Xen_RR-SAP) which shows odds=0.248 (p<0.001) (Mollura p. 3, Table 1), wherein as Mollura measures sample entropy of both systolic arterial pressure and diastolic arterial pressure, the measured sample entropy of each are considered to include a time when systolic MAP is reached (See corresponding § 112(b) rejection and interpretation of claim 7 above)].
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Newberry to employ wherein the set of extracted features also comprises kurtosis of pressure distribution and sample entropy of the time when systolic MAP is reached, as Song and Mollura indicate that kurtosis of pressure distribution and sample entropy of the time when systolic MAP is reached are considered to be relevant in screening for sepsis.
Claim(s) 8 is/are rejected under 35 U.S.C. 103 as being unpatentable over Newberry, as applied to claim 1 above, in further view of Garcia et al. (“Dynamic Arterial Elastance During Experimental Endotoxic Septic Shock: A Potential Marker of Cardiovascular Efficiency”, NPL attached), hereinafter Garcia, Mollura, and Rassias et al. (“Hydrocortisone at stress-associated concentrations helps maintain human heart rate variability during subsequent endotoxin challenge”, NPL attached), hereinafter Rassias.
Regarding claim 8, Newberry teaches
The computational method of claim 1, wherein the set of extracted features comprises heart rate [Newberry ¶0325].
However, Newberry fails to explicitly disclose wherein the set of extracted features also comprises arterial tone factor, sample entropy of decay area, dynamic arterial elastance, and approximate entropy of time of systole.
Garcia discloses methods for assessing parameters indicative of sepsis, wherein Garcia notes that septic animals showed a significant decrease in arterial tone [Septic animals also showed a significant decrease in arterial tone, as reflected by an increase in net arterial compliance (Garcia p. 10)]; and wherein Garcia indicates that dynamic arterial elastance increased during endotoxic septic shock and was further related to cardiovascular efficiency during endotoxic shock [In this experimental animal study, Eadyn increased during endotoxic septic shock and decreased after hemodynamic resuscitation (Garcia p. 7); During experimental endotoxic shock, Eadyn changes were associated with arterial and cardiac factors and significantly related to cardiovascular efficiency: the higher the efficiency of the cardiovascular system on delivering the energy to the arterial system for sustaining blood flow, the higher the Eadyn. Therefore, Eadyn may be a valuable index for monitoring cardiovascular mechanical efficiency (Garcia p. 13)].
Mollura discloses methods for identifying septic patients, wherein Mollura depicts systolic arterial pressure as decaying in [In Fig. 1 are shown ECG and ABP traces from two distinct subjects: a septic (upper) and a control (lower) subject with Xen_RR-SS equal to 0.1698 and 7.272, respectively. The high overall blood pressure variability, please note the difference in the two scales, and the stronger synchronization between RR and SAP time series can be appreciated in the septic traces with respect to the control ones (Mollura p. 3)], wherein Mollura further determines sample entropy of systolic arterial pressure to differentiate between patients with sepsis and control patients [Sample entropy measures computed on pressure time series (SAP_SampEn and DAP_SampEn) result statistically significant (p<0.01 and p<0.05) when comparing the two populations, showing both odds<1 for unitary increase as well as cross-sample entropy from RR and SAP series (Xen_RR-SAP) which shows odds=0.248 (p<0.001) (Mollura p. 3, Table 1), wherein as Mollura measures sample entropy of systolic arterial pressure, the measured sample entropy is considered to include a time of systole]; wherein based on the plain definition of “decay” referring “to decline in health, strength, or vigor; to decrease usually gradually in size, quantity, activity, or force” [and further lack of a particular definition of “decay area” by the Applicant], as Mollura determines sample entropy of the time series of systolic arterial pressure of patients with sepsis, wherein systolic arterial pressure decreases over time, the sample entropy as determined is considered to refer to “sample entropy of decay area”.
Rassias discloses methods for analyzing heart rate variability during a systemic inflammatory status, wherein Rassias discloses that heart rate variability is a parameter indicative of sepsis [a decrease in HRV predicts rapid changes in blood pressure and elevated levels of inflammatory cytokines in patients with sepsis and predicts outcomes and mortality after a septic episode (Rassias p. 2); Multiple aspects of HRV alterations in sepsis have been investigated… With this background, HRV has been examined as a means to predict poor clinical outcomes. A clinical diagnosis of neonatal sepsis, for example, is preceded by alterations in HRV dynamics… Clinical outcomes in adult patients who are more likely to develop sepsis upon presentation to an emergency department can be predicted by alterations in time-domain or frequency-domain measures of HRV [19]. Furthermore, patients admitted to an intensive care unit with a diagnosis of sepsis are likely to develop multiple organ dysfunctions if time-domain or frequency-domain measures of HRV are abnormal upon admission (Rassias p. 4), wherein heart rate variability is considered to be based on time of systole], and further discloses that approximate entropy is a known statistical measure of data [We performed the analysis of HRV with the well-known statistic ApEn. This approach has the advantages of standardization as well as the fact that it is valid with data sets of varying sizes (Rassias p. 4)].
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Newberry to employ wherein the set of extracted features also comprises arterial tone factor, sample entropy of decay area, dynamic arterial elastance, and approximate entropy of time of systole, as Garcia and Mollura indicate arterial tone factor, sample entropy of decay area, dynamic arterial elastance as being indicative of sepsis, and as Rassias indicates that heart rate variability, which is considered to be defined by time of systole, is considered to be indicative of sepsis and may be statistically assessed using approximate entropy.
Subject Matter Not Taught By Prior Art
The following is a statement of reasons for the indication of subject matter considered to not be taught by prior art:
Newberry discloses methods for using a prediction model to determine a screening score of sepsis [Newberry ¶0322], wherein Newberry discloses at least heart rate as a relevant parameter in screening for sepsis [Newberry ¶0325].
Song, Mollura, Garcia, and Rassias each disclose different parameters that may be indicative of sepsis [Song p. 3, 12, Tables 4-5; Mollura p. 3, Table 1, Fig. 1; Garcia p. 10, 13; Rassias p. 2, 4; See also Examiner’s analysis of the identified parameters in the rejections of claim 7-8 under § 103 above].
Osypka (WO-2017029396-A1, foreign reference attached) discloses systems and methods for differentiating between different shock types, including septic shock, wherein Osypka discloses relevant parameters for differentiating between different shock types include: heart rate, mean arterial blood pressure, systolic time ratio, as well as further parameters derived from such values, such as sample entropy and other statistical measures [In a shock type differentiation system, the different shock probabilities may be determined based on selected groups of hemodynamic and other parameters which may the same or different for different shock types, in particular, but not limited to, heart rate, stroke volume, cardiac output, mean arterial blood pressure, predictors of fluid responsiveness such as stroke volume, stroke volume variation, pleth variability index and pulse pressure variation, cardiac contractility or index of contractility, cardiac output, thoracic fluid content, flow time, systolic time ratio, systemic vascular resistance, temperature, respiration rate, ventilation rate, or a subset of the foregoing values, or a combination of such patient hemodynamic values and further parameters derived from such values, such as sample entropy and other statistical measures, and the patient's demographic data (i.e., gender, age, body mass or weight, height). Other parameters which may be incorporated may be based on blood tests, organ failure, or the medical history of the patient. Respective software modules are configured to calculate probability of generic shock, cardiogenic shock, hypovolemic shock, septic shock, and anaphylactic shock, respectively (Osypka ¶017)].
However, none of Newberry, Song, Mollura, Garcia, Rassias, or Osypka, alone or in combination, teach, disclose, or suggest the particularity of the claimed “ScreeningScore” equations of claims 10-11, such that it would not have been obvious to one of ordinary skill in the art to have modified any of Newberry, Osypka, or Song, alone or in combination, to employ the particularity of the claimed “ScreeningScore” equations of claims 10-11 without the benefit of hindsight. As such, the subject matter of claims 10-11 are not considered to be taught by any prior art reference.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SEVERO ANTONIO P LOPEZ whose telephone number is (571)272-7378. The examiner can normally be reached M-F 9-6 EST.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Charles Marmor II can be reached at (571) 272-4730. 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.
/SEVERO ANTONIO P LOPEZ/Examiner, Art Unit 3791
Prosecution Insights