DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application is being examined under the pre-AIA first to invent provisions.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 11/03/2022 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Response to Arguments
101 Rejection Arguments
Applicant asserts:
Applicant argues, on page 8-14, that amended claim 1 is not directed to mere observation or judgment. Rather, claim 1 recites a specific technological improvement in the technical area of taking a blood pressure.
Examiner response:
Examiner respectfully disagrees and notes MPEP 2106.04(d)(1) states that a bare assertion of an improvement is not sufficient in stating a claim is set forth to a technological improvement. Examiner notes that the claims and specification do not provide the detail necessary to be apparent to a person of ordinary skill in the art of the improvement.
The claimed do not provide an improvement to the technology, instead the examiner’s analysis is similar to Recentive Analytics because the claims use machine learning at a high level.
103 Rejection Arguments
Applicant asserts:
Applicant argues, on page 14-18, that Xiaoman, Lucas, Huang, Jason, and Junwen, whether taken alone or in combination, fail to teach and/or suggest all limitations of amended claim 1.
Examiner response:
In response to applicant's arguments against the references individually regarding the limitations of dynamically converting, determining, generating, and extracting, one cannot show nonobviousness by attacking references individually where the rejections are based on combinations of references. See In re Keller, 642 F.2d 413, 208 USPQ 871 (CCPA 1981); In re Merck & Co., 800 F.2d 1091, 231 USPQ 375 (Fed. Cir. 1986).
Regarding the last generating step, Arguments have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
In reference to claim 1:
Step 1 - Is the claim to a process, machine, manufacture or composition of matter?
Yes, the claim is directed to a process
Step 2A Prong 1 - Does the claim recite an abstract idea, law of nature, or natural phenomenon?
“dynamically converting, by the at least one processor, at least one digital PPG sample of the plurality of digital PPG samples into at least one visibility node in a plurality of visibility nodes based on a plurality of time series vectors associated with the plurality of digital PPG samples;” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could convert the data into visibility nodes based on time series vectors associated with the plurality of PPG sample data.
“determining, by the at least one processor, a visibility graph comprising a plurality of visibility edges amongst the plurality of visibility nodes based at least in part on a visibility between each visibility node of a plurality of candidate visibility node pairs;” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could determine a visibility graph from visibility nodes and visibility edges.
“generating, by the at least one processor, utilizing the plurality of visibility nodes and the plurality of visibility edges, at least one image to represent visibility graph of the plurality of time series vectors associated with the time window of the digital PPG signal data” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could generate an image to represent the visibility graph; the visibility graph itself is an image.
“extracting, by the at least one processor, [using a pre-trained image analysis machine learning model], at least one feature metric of a plurality of feature metrics from the at least one image” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could evaluate the image and extract feature metrics.
“generating, by the at least one processor, utilizing the a regression transfer learning algorithm, at least one blood pressure estimation associated with the time window a second position of the at least one node in the plurality of nodes based at least in part on: the at least one feature metric, and the analysis of the pre-trained machine learning algorithm and the at least one pre-trained relation between the at least one feature metric and the at least one image time series vector; wherein the at least one pre-trained relation comprises at least one weight, at least one bias, or both based at least in part on: the at least one prior feature metric extracted from at least one prior visibility graph, and the at least one reference blood pressure.” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could generate a blood pressure estimation using a regression transfer algorithm based on analysis of various parameters.
Step 2A Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application?
“A computer-implemented method for cuff-less blood pressure estimation from digital photoplethysmography (PPG) signal data, the method comprising: [receiving], by at least one processor, [a plurality of digital PPG samples of a time window of the digital PPG signal data from at least one PPG sensor device of a plurality of sensor devices;]” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
“receiving, by at least one processor, a plurality of digital PPG samples of a time window of the digital PPG signal data from at least one PPG sensor device of a plurality of sensor devices;” (insignificant extra-solution activity mere data gathering MPEP 2106.05(g))
“using a pre-trained image analysis machine learning model” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
The claim does not include additional elements that are integrated into a practical application.
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception?
“A computer-implemented method for cuff-less blood pressure estimation from digital photoplethysmography (PPG) signal data, the method comprising: [receiving], by at least one processor, [a plurality of digital PPG samples of a time window of the digital PPG signal data from at least one PPG sensor device of a plurality of sensor devices;]” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
“receiving, by at least one processor, a plurality of digital PPG samples of a time window of the digital PPG signal data from at least one PPG sensor device of a plurality of sensor devices;” (well-understood, routine, conventional MPEP 2106.05(d))
“using a pre-trained image analysis machine learning model” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
In reference to claim 2:
Claim 2 is directed to a judicial exception from claim(s) depended on and does not recite additional elements that integrate the judicial exception into a practical application and amount to significantly more than the judicial exception.
In reference to claim 3:
Claim 3 is directed to a judicial exception from claim(s) depended on and does not recite additional elements that integrate the judicial exception into a practical application and amount to significantly more than the judicial exception.
In reference to claim 4:
Claim 4 is directed to a judicial exception from claim(s) depended on and does not recite additional elements that integrate the judicial exception into a practical application and amount to significantly more than the judicial exception.
In reference to claim 6:
Claim 6 is directed to a judicial exception from claim(s) depended on and does not recite additional elements that integrate the judicial exception into a practical application and amount to significantly more than the judicial exception.
In reference to claim 7:
Claim 7 is directed to a judicial exception from claim(s) depended on and does not recite additional elements that integrate the judicial exception into a practical application and amount to significantly more than the judicial exception.
In reference to claim 8:
Claim 8 is directed to a judicial exception from claim(s) depended on and does not recite additional elements that integrate the judicial exception into a practical application and amount to significantly more than the judicial exception.
In reference to claim 9:
Step 1 - Is the claim to a process, machine, manufacture or composition of matter?
Yes, the claim is directed to a process
Step 2A Prong 1 - Does the claim recite an abstract idea, law of nature, or natural phenomenon?
“The computer-implemented method of claim 1, further comprising applying a selection procedure to the plurality of digital signal data to remove at least one of: duplicated digital signal data, at least one error in the digital PPG signal data, or digital signal with less than a predetermined number of systolic peaks.” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could apply a selection procedure to plurality of digital signal data.
Step 2A Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application?
No
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception?
No
In reference to claim 10:
Step 1 - Is the claim to a process, machine, manufacture or composition of matter?
Yes, the claim is directed to a process
Step 2A Prong 1 - Does the claim recite an abstract idea, law of nature, or natural phenomenon?
“The computer-implemented method of claim 1, further comprising classifying the feature metric into one of at least two classes.” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could classify feature metrics into at least two classes.
Step 2A Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application?
No
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception?
No
In reference to claim 11:
Step 1 - Is the claim to a process, machine, manufacture or composition of matter?
Yes, the claim is directed to a manufacture
Step 2A Prong 1 - Does the claim recite an abstract idea, law of nature, or natural phenomenon?
“dynamically convert at least one digital PPG sample of the plurality of digital PPG samples into at least one visibility node in a plurality of visibility nodes based on a plurality of time series vectors associated with the plurality of digital PPG samples;” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could convert the data into visibility nodes based on time series vectors associated with the plurality of PPG sample data.
“determine a visibility graph comprising a plurality of visibility edges amongst the plurality of visibility nodes based at least in part on a visibility between each visibility node of a plurality of candidate visibility node pairs;” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could determine a visibility graph from visibility nodes and visibility edges.
“generate, utilizing the plurality of visibility nodes and the plurality of visibility edges, at least one image to represent visibility graph of the plurality of time series vectors associated with the time window of the digital PPG signal data” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could generate an image to represent the visibility graph; the visibility graph itself is an image.
“extract [using a pre-trained image analysis machine learning model], at least one feature metric of a plurality of feature metrics from the at least one image” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could evaluate the image and extract feature metrics.
“generating, utilizing the a regression transfer learning algorithm, at least one blood pressure estimation associated with the time window a second position of the at least one node in the plurality of nodes based at least in part on: the at least one feature metric, and the analysis of the pre-trained machine learning algorithm and the at least one pre-trained relation between the at least one feature metric and the at least one image time series vector; wherein the at least one pre-trained relation comprises at least one weight, at least one bias, or both based at least in part on: the at least one prior feature metric extracted from at least one prior visibility graph, and the at least one reference blood pressure.” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could generate a blood pressure estimation using a regression transfer algorithm based on analysis of various parameters.
Step 2A Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application?
“A system for cuff-less blood pressure estimation from digital photoplethysmography (PPG) signal data, the system comprising: at least one processor configured to execute software instructions, wherein the software instructions, when executed, cause the at least one processor to perform steps to:” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
“receive a plurality of digital PPG samples of a time window of the digital PPG signal data from at least one PPG sensor device of a plurality of sensor devices;” (insignificant extra-solution activity mere data gathering MPEP 2106.05(g))
“using a pre-trained image analysis machine learning model” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
The claim does not include additional elements that are integrated into a practical application.
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception?
“A system for cuff-less blood pressure estimation from digital photoplethysmography (PPG) signal data, the system comprising: at least one processor configured to execute software instructions, wherein the software instructions, when executed, cause the at least one processor to perform steps to:” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
“receive a plurality of digital PPG samples of a time window of the digital PPG signal data from at least one PPG sensor device of a plurality of sensor devices;” (well-understood, routine, conventional MPEP 2106.05(d))
“using a pre-trained image analysis machine learning model” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
In reference to claim 12:
Claim 12 is directed to a judicial exception from claim(s) depended on and does not recite additional elements that integrate the judicial exception into a practical application and amount to significantly more than the judicial exception.
In reference to claim 13:
Claim 13 is directed to a judicial exception from claim(s) depended on and does not recite additional elements that integrate the judicial exception into a practical application and amount to significantly more than the judicial exception.
In reference to claim 14:
Claim 14 is directed to a judicial exception from claim(s) depended on and does not recite additional elements that integrate the judicial exception into a practical application and amount to significantly more than the judicial exception.
In reference to claim 16:
Claim 16 is directed to a judicial exception from claim(s) depended on and does not recite additional elements that integrate the judicial exception into a practical application and amount to significantly more than the judicial exception.
In reference to claim 17:
Claim 17 is directed to a judicial exception from claim(s) depended on and does not recite additional elements that integrate the judicial exception into a practical application and amount to significantly more than the judicial exception.
In reference to claim 18:
Claim 18 is directed to a judicial exception from claim(s) depended on and does not recite additional elements that integrate the judicial exception into a practical application and amount to significantly more than the judicial exception.
In reference to claim 19:
Step 1 - Is the claim to a process, machine, manufacture or composition of matter?
Yes, the claim is directed to a manufacture
Step 2A Prong 1 - Does the claim recite an abstract idea, law of nature, or natural phenomenon?
“The system of claim 11, wherein the software instructions, when executed, further cause the at least one processor to perform steps to: apply a selection procedure to the plurality of digital signal data to remove at least one of: duplicated digital signal data, at least one error in the digital PPG signal data, or digital signal with less than a predetermined number of systolic peaks.” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could apply a selection procedure to plurality of digital signal data.
Step 2A Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application?
No
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception?
No
In reference to claim 20:
Step 1 - Is the claim to a process, machine, manufacture or composition of matter?
Yes, the claim is directed to a manufacture
Step 2A Prong 1 - Does the claim recite an abstract idea, law of nature, or natural phenomenon?
“The system of claim 11, wherein the software instructions, when executed, further cause the at least one processor to perform steps to classify the feature metric into one of at least two classes.” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could classify feature metrics into at least two classes.
Step 2A Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application?
No
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception?
No
In reference to claim 21:
Step 1 - Is the claim to a process, machine, manufacture or composition of matter?
Yes, the claim is directed to a process
Step 2A Prong 1 - Does the claim recite an abstract idea, law of nature, or natural phenomenon?
“The method of claim 1, wherein the regression algorithm is trained by: applying ridge regression or model fine-tuning or both to the at least one prior feature metric extracted from the at least one prior visibility graph generated from the at least one prior digital PPG signal data and paired reference blood pressure values, and the at least one pre-trained relation between the at least one feature metric and the at least one image, to solve for the at least one weight, the at least one bias, or both.” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could apply a ridge expression to a feature metric and the pre-trained relation between the feature metric and the image to solve a weight.
Step 2A Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application?
No
The claim does not include additional elements that are integrated into a practical application.
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception?
No
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
In reference to claim 22:
Step 1 - Is the claim to a process, machine, manufacture or composition of matter?
Yes, the claim is directed to a manufacture
Step 2A Prong 1 - Does the claim recite an abstract idea, law of nature, or natural phenomenon?
“The system of claim 11, wherein the regression algorithm is trained by: applying ridge regression or model fine-tuning or both to the at least one prior feature metric extracted from the at least one prior visibility graph generated from the at least one prior digital PPG signal data and paired reference blood pressure values, and the at least one pre-trained relation between the at least one feature metric and the at least one image, to solve for the at least one weight, the at least one bias, or both.” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could apply a ridge expression to a feature metric and the pre-trained relation between the feature metric and the image to solve a weight.
Step 2A Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application?
No
The claim does not include additional elements that are integrated into a practical application.
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception?
No
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1-4, 6-14, and 16-20 are rejected under 35 U.S.C. 103 as being unpatentable over Xiaoman et al; “An Unobtrusive and Calibration-free Blood Pressure Estimation Method using Photoplethysmography and Biometrics” (hereinafter “Xiaoman”) in view of Lucas et al; “From time series to complex networks: the visibility graph” (hereinafter “Lucas”) in further view of Randy et al; US 11868878 B1 (hereinafter “Randy”) in further view of Lars Schmitt et al; US 20200229716 A1 (hereinafter “Schmitt”)
Regarding claim 1, Xiaoman teaches A computer-implemented method for cuff-less blood pressure estimation from digital photoplethysmography (PPG) signal data, the method comprising: receiving, by at least one processor, a plurality of digital PPG samples of a time window of the digital PPG signal data from at least one PPG sensor device of a plurality of sensor devices; (Xiaoman Section "PPG and BP measurement procedures" Paragraph 1; "In this study, the PPG waveform was measured by a validated medical pulse oximeter (BM2000A from Shanghai Berry Electronic Technology Co., Ltd), with a modified receiving protocol to record raw data… PPG was sampled at 50 Hz, …each subject was measured for at least 60 seconds" Xiaoman Section "PPG and BP measurement procedures" Paragraph 3;"The purpose of this study is to collect as many data as possible to build a best-performing model, and evaluate its applicability. It’s not meant to validate a specific BP measuring device or algorithm, so we did not follow the standard validation procedure for BP measuring devices" Examiner notes that plurality of digital PPG samples (PPG sampled at 50 Hz) of a time window of the digital PPG signal data (PPG data is measured for 60 seconds) is received/receiving protocol to record raw data from at least one PPG sensor device/medical pulse oximeter of a plurality of sensor devices/Paragraph 3 suggests multiple measuring devices used; medical pulse oximeter contains a processor and receives data)
Dynamically (Xiaoman Section "Discussion" Paragraph 1; "This technological breakthrough helps us make extremely small, comfortable, noninvasive and inexpensive devices, which will facilitate its widespread application in continuous BP monitoring and cardiovascular health management." Examiner notes that continuous BP monitoring means dynamic processing)
Xiaoman does not teach [dynamically] converting, by the at least one processor, at least one digital [PPG] sample of the plurality of digital [PPG] samples into at least one visibility node in a plurality of visibility nodes based on a plurality of time series vectors associated with the plurality of digital [PPG] samples;
determining, by the at least one processor, a visibility graph comprising a plurality of visibility edges amongst the plurality of visibility nodes based at least in part on a visibility between each visibility node of a plurality of candidate visibility node pairs;
generating, by the at least one processor, utilizing the plurality of visibility nodes and the plurality of visibility edges, at least one image to represent visibility graph of the plurality of time series vector associated with the time window of the digital [PPG] signal data,
However, Lucas does teach [dynamically] converting, by the at least one processor, at least one digital [PPG] sample of the plurality of digital [PPG] samples into at least one visibility node in a plurality of visibility nodes based on a plurality of time series vectors associated with the plurality of digital [PPG] samples; (Lucas “Resumen”; “In this work we present a simple and fast computational method, the visibility algorithm” Lucas Page 1 Paragraph 2; "we plot the first twenty values of a periodic series using vertical bars (the data values are displayed above the plot). Considering this as a landscape, we link every bar (every point of the time series) with all those that can be seen from the top of the considered one (gray lines)" Examiner notes that at least one digital PPG sample of the plurality of PPG sample/first twenty values are converted into at least one visibility node/node at the top of bar in a plurality of visibility node/every point on each bar based a plurality of time series vectors/every bar of every point associated with the plurality of PPG samples/converted from signal data; the algorithm is a computational method meaning a processor performs the algorithm)
determining, by the at least one processor, a visibility graph comprising a plurality of visibility edges amongst the plurality of visibility nodes based at least in part on a visibility between each visibility node of a plurality of candidate visibility node pairs; (Lucas Paragraph 2; “we present a scheme of the visibility algorithm. In the upper zone we plot the first twenty values of a periodic series using vertical bars (the data values are displayed above the plot). Considering this as a landscape, we link every bar (every point of the time series) with all those that can be seen from the top of the considered one (gray lines), obtaining the associated graph (shown in the lower part of the figure). In this graph, every node corresponds, in the same order, to a series data, and two nodes are connected if there exists visibility between the corresponding data, that is to say, if there is a straight line that connects the series data, provided that this “visibility line” does not intersect any intermediate data height. More formally, we can establish the following visibility criterium: two arbitrary” Examiner notes that a visibility graph (associated graph (shown in the lower part of the figure)) is determined, by the visibility algorithm, comprising a plurality of visibility edges (visibility line) amongst the plurality of visibility nodes (every point/node on top each bar) based at least in part on a visibility between each visibility node of a plurality of candidate visibility node pairs (every node corresponds, in the same order, to a series data, and two nodes are connected if there exists visibility between the corresponding data, that is to say, if there is a straight line that connects the series data, provided that this “visibility line” does not intersect any intermediate data height))
generating, by the at least one processor, utilizing the plurality of visibility nodes and the plurality of visibility edges, at least one image to represent visibility graph of the plurality of time series vector associated with the time window of the digital [PPG] signal data,; (Lucas Page 1 Paragraph 2; "we link every bar (every point of the time series) with all those that can be seen from the top of the considered one (gray lines), obtaining the associated graph (shown in the lower part of the figure). " Lucas Page 10 Figure 2; "The visibility graph of a time series remains invariant under several transformation of the time series" Examiner notes that utilizing the plurality of visibility nodes (every point of the time series) and the plurality of visibility edges (link every bar with those that can be seen from the top), generating/obtaining at least one image/associated graph to represent the visibility graph (visibility graph of a time series) of the plurality of time series vectors (bar for every point) associated with the time window of the digital signal data (time window of first 20 values); time series vectors are represented as lines and lines are a 2d shape)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Xiaoman and Lucas. Xiaoman teaches a novel paradigm to unobtrusively and optically measure blood pressure (BP) without calibration. Lucas teaches converting time series data into visibility graphs. One of ordinary skill would have motivation to combine Xiaoman and Lucas to convert the time blood pressure data into visibility graphs to reveal non trivial information about the data “this network inherits several properties of the time series, and its study reveals non trivial information about the series itself.” (Lucas Page 1 Paragraph 1).
Xiaoman in view of Lucas does not teach extracting, by the at least one processor, using a pre-trained image analysis machine learning model, at least one feature metric of a plurality of feature metrics from the at least one image
and at least one pre-trained relation between the at least one feature metric and the at least one image wherein the at least one pre-trained relation comprises at least one weight, at least one bias, or both
based at least in part on: the at least one prior feature metric extracted from at least one prior [visibility] graph, [and the at least one reference blood pressure].
However, Randy does teach extracting, by the at least one processor, using a pre-trained image analysis machine learning model, at least one feature metric of a plurality of feature metrics from the at least one image (Randy Column 9 Paragraph 2; "The convolution operations in a CNN may be used to extract features from input image 310." Randy Column 24 Paragraph 3; "a general purpose computer with instruction code, or a computing system as described below with respect to FIG. 12. The instruction code may be stored on a non-transitory storage medium (e.g., on a memory device)." Examiner notes that CNN/pre-trained machine learning algorithm is used to analyze the image and extract at least one feature metric of a plurality of feature metrics/features from the at least one image/input image; method includes processor that executes instruction code for extraction and following claimed functions)
and at least one pre-trained relation between the at least one feature metric and the at least one image wherein the at least one pre-trained relation comprises at least one weight, at least one bias, or both (Randy Column 10 Paragraph 4; “a CNN may learn the weights of the filters on its own during the training process based on some user specified parameters (which may be referred to as hyperparameters) before the training process, such as the number of filters, the filter size, the architecture of the network, etc. The more number of filters used, the more image features may get extracted, and the better the network may be at recognizing patterns in new images.” Examiner notes that the at least one pre-trained relation (CNN may learn the weights of the filters on its own during the training process) between the at least one feature metric (image features) and the at least one image (new images) wherein the at least one pre-trained relation comprises at least one weight (CNN may learn weights); being based on the feature metric is also based on the relation between the feature metric and image because the feature metric is extracted from the image)
based at least in part on: the at least one prior feature metric extracted from at least one prior [visibility] graph, [and the at least one reference blood pressure]. (Randy Column 13 Paragraph 2; “use the gradient descent to update parameters and weights to be trained in the network to minimize the output error… When the same training sample is input again, the output probabilities might be closer to the target probabilities, which indicates that the network has learned to classify this particular image.” Examiner notes that the weights is based at least in part on the at least one prior feature metric (output probabilities of previous training) extracted from at least one prior graph (particular image))
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Xiaoman, Lucas, and Randy. Xiaoman teaches a novel paradigm to unobtrusively and optically measure blood pressure (BP) without calibration.. Lucas teaches converting time series data into visibility graphs. Randy teaches the use of artificial neural networks to classify objects in an image. One of ordinary skill would have motivation to combine Xiaoman, Lucas, and Randy to leverage artificial neural network capabilities in the medical field “An artificial neural network (ANN) is a computational system that is inspired by the way biological neural networks in the human brain process information. Artificial neural networks have been used in machine learning research and industrial applications and have achieved many breakthrough results in, for example, image recognition, speech recognition, computer vision, text processing, etc.” (Randy Column 4 Paragraph 1).
Xiaoman in view of Lucas in further view of Randy does not teach and generating, by the at least one processor, utilizing a regression algorithm, at least one blood pressure estimation associated with the time window based at least in part on the at least one feature metric,
[and at least one pre-trained relation between the at least one feature metric and the at least one image] wherein the at least one pre-trained relation comprises at least one weight, at least one bias, or both based at least in part on: [the at least one prior feature metric extracted from at least one prior visibility graph, and] the at least one reference blood pressure
However, Schmitt does teach and generating, by the at least one processor, utilizing a regression algorithm, at least one blood pressure estimation associated with the time window based at least in part on the at least one feature metric, (Schmitt Paragraph 0018; “a non-transitory computer-readable recording medium that stores therein a computer program product, which, when executed by a processor, causes the method disclosed herein to be performed.” Schmitt Paragraph 0025; “Features that show good correlation with blood pressure may be selected and for each selected feature a blood pressure estimation value can be calculated (e.g. via regression according to a mathematical model, using again the blood pressure reference measurements).” Schmitt Paragraph 0057; “The selection of features is based on functions that can be applied to the PPG waveform signal and provide a feature value. As an example, the feature time_deri2a (time from maximum of first derivate to minimum of dicrotic notch)” Examiner notes that processor executes the step of utilizing a regression algorithm (via regression according to a mathematical model) to generate at least one blood pressure estimation (blood pressure estimation value) associated with the time window (time from maximum of first derivate to minimum of dicrotic notch) is based at least in part on the at least one feature metric (feature that show good correlation))
[and at least one pre-trained relation between the at least one feature metric and the at least one image] wherein the at least one pre-trained relation comprises at least one weight, at least one bias, or both based at least in part on: [the at least one prior feature metric extracted from at least one prior visibility graph, and] the at least one reference blood pressure (Schmitt Paragraph 0025; “Preferably, the estimation unit is configured to determine the subject's blood pressure by taking a weighted average of some or all of said multiple blood pressure estimation values, wherein said weights used for said weighted average are determined based on a correlation between a subject's blood pressure and its corresponding feature” Examiner notes that the weights are based at least in part of the at least one reference blood pressure (subject’s blood pressure))
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Xiaoman, Lucas, Randy, and Schmitt. Xiaoman teaches a novel paradigm to unobtrusively and optically measure blood pressure (BP) without calibration. Lucas teaches converting time series data into visibility graphs. Randy teaches the use of artificial neural networks to classify objects in an image. Schmitt teaches method for determining blood pressure of a subject. One of ordinary skill would have motivation to combine Xiaoman, Lucas, Randy, and Schmitt to improve the feature selection process “the feature selection process can be improved by utilizing the signal-to-noise ratio of the measured features. For example, if the signal-to-noise ratio of the measured features is low, then the measured correlation coefficient or the measured regression error can be penalized by proper weighting factors.” (Schmitt Paragraph 0071).
Regarding claim 2, Xiaoman teaches The computer-implemented method of claim 1, wherein the plurality of digital signal data comprises a plurality of physiological data signals. (Xiaoman Section "PPG and BP measurement procedure" Paragraph 1; "In this study, the PPG waveform was measured by a validated medical pulse oximeter")
Regarding claim 3, Xiaoman does not teach The computer-implemented method of claim 1, wherein the plurality of visibility nodes preserves a plurality of temporal information associated with a data waveform based on the plurality of digital signal data.
However, Lucas does teach The computer-implemented method of claim 1, wherein the plurality of visibility nodes preserves a plurality of temporal information associated with a data waveform based on the plurality of digital signal data. (Lucas Page 2 Paragraph 3; "In the case of periodic time series, its regularity seems therefore to be conserved or inherited structurally in the graph by means of the visibility map." Examiner notes that the plurality of visibility node in the visibility map preserves a plurality of temporal information/regularity is conserved or inherited structurally associated with a data waveform/structure of graph based on the plurality of digital signal data)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Xiaoman and Lucas. Xiaoman teaches a novel paradigm to unobtrusively and optically measure blood pressure (BP) without calibration.. Lucas teaches converting time series data into visibility graphs. One of ordinary skill would have motivation to combine Xiaoman and Lucas to convert the time blood pressure data into visibility graphs to reveal non trivial information about the data “this network inherits several properties of the time series, and its study reveals non trivial information about the series itself.” (Lucas Page 1 Paragraph 1).
Regarding claim 4, Xiaoman does not teach The computer-implemented method of claim 1, wherein the pre-trained machine learning algorithm comprises a deep conventional neural network.
However, Randy does teach The computer-implemented method of claim 1, wherein the pre-trained machine learning algorithm comprises a deep conventional neural network. (Randy Column 7 Paragraph 5; "LeNet developed by Yann LeCun et al. in 1990s for hand-written number recognition is one of the first convolutional neural networks that helped propel the field of deep learning." Examiner notes that CNN/pre-trained machine learning algorithm comprises/is a deep conventional neural network)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Xiaoman, Lucas, and Randy. Xiaoman teaches a novel paradigm to unobtrusively and optically measure blood pressure (BP) without calibration.. Lucas teaches converting time series data into visibility graphs. Randy teaches the use of artificial neural networks to classify objects in an image. One of ordinary skill would have motivation to combine Xiaoman, Lucas, and Randy to leverage artificial neural network capabilities in the medical field “An artificial neural network (ANN) is a computational system that is inspired by the way biological neural networks in the human brain process information. Artificial neural networks have been used in machine learning research and industrial applications and have achieved many breakthrough results in, for example, image recognition, speech recognition, computer vision, text processing, etc.” (Randy Column 4 Paragraph 1).
Regarding claim 6, Xiaoman does not teach The computer-implemented method of claim 1, wherein the pre-trained learning algorithm is one of AlexNet, VGG-19 or Inception v3.
However, Randy does teach The computer-implemented method of claim 1, wherein the pre-trained learning algorithm is one of AlexNet, VGG-19 or Inception v3. (Randy Column 13 Paragraph 4; "There may be many variations and improvements to CNN 300 described above, such as AlexNet")
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Xiaoman, Lucas, and Randy. Xiaoman teaches a novel paradigm to unobtrusively and optically measure blood pressure (BP) without calibration.. Lucas teaches converting time series data into visibility graphs. Randy teaches the use of artificial neural networks to classify objects in an image. One of ordinary skill would have motivation to combine Xiaoman, Lucas, and Randy to leverage artificial neural network capabilities in the medical field “An artificial neural network (ANN) is a computational system that is inspired by the way biological neural networks in the human brain process information. Artificial neural networks have been used in machine learning research and industrial applications and have achieved many breakthrough results in, for example, image recognition, speech recognition, computer vision, text processing, etc.” (Randy Column 4 Paragraph 1).
Regarding claim 7, Xiaoman teaches The computer-implemented method of claim 1, wherein the plurality of digital signal data comprises the PPG data and reference BP data. (Xiaoman Section "PPG and BP measurement procedure" shows that plurality of digital signal data is/comprises PPG data and reference BP data)
Regarding claim 8, Xiaoman does not teach The computer-implemented method of claim 1, wherein the at least one image is a visibility graph (VG).
However, Lucas does teach The computer-implemented method of claim 1, wherein the at least one image is a visibility graph (VG). (Lucas Page 9 Figure 1 shows that image is a visibility graph)
PNG
media_image1.png
375
614
media_image1.png
Greyscale
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Xiaoman and Lucas. Xiaoman teaches a novel paradigm to unobtrusively and optically measure blood pressure (BP) without calibration.. Lucas teaches converting time series data into visibility graphs. One of ordinary skill would have motivation to combine Xiaoman and Lucas to convert the time blood pressure data into visibility graphs to reveal non trivial information about the data “this network inherits several properties of the time series, and its study reveals non trivial information about the series itself.” (Lucas Page 1 Paragraph 1).
Regarding claim 9, Xiaoman teaches The computer-implemented method of claim 1, further comprising applying a selection procedure to the plurality of digital signal data to remove at least one of: duplicated digital signal data, at least one error in the digital PPG signal data, or digital signal with less than a predetermined number of systolic peaks. (Xiaoman Section "Data Selection" Paragraph 1; "If one feature from a particular beat was considered an outlier, this particular beat was labeled abnormal and discarded. If the percentage of abnormal beats for a measurement exceeded 20%, the entire measurement was excluded.")
Regarding claim 10, Xiaoman does not teach The computer-implemented method of claim 1, further comprising classifying the feature metric into one of at least two classes.
However, Randy does teach The computer-implemented method of claim 1, further comprising classifying the feature metric into one of at least two classes. (Randy Column 12 Paragraph 3; "Fully-connected layer 360 may use the high-level features of the input image represented by output matrices 350 to classify the input image into various classes based on the training dataset." Examiner notes that the feature metric/features are being classified into one of at least two classes/various classes)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Xiaoman, Lucas, and Randy. Xiaoman teaches a novel paradigm to unobtrusively and optically measure blood pressure (BP) without calibration.. Lucas teaches converting time series data into visibility graphs. Randy teaches the use of artificial neural networks to classify objects in an image. One of ordinary skill would have motivation to combine Xiaoman, Lucas, and Randy to leverage artificial neural network capabilities in the medical field “An artificial neural network (ANN) is a computational system that is inspired by the way biological neural networks in the human brain process information. Artificial neural networks have been used in machine learning research and industrial applications and have achieved many breakthrough results in, for example, image recognition, speech recognition, computer vision, text processing, etc.” (Randy Column 4 Paragraph 1).
Regarding claim 11, Xiaoman teaches receive a plurality of digital PPG samples of a time window of the digital PPG signal data from at least one PPG sensor device of a plurality of sensor devices; (Xiaoman Section "PPG and BP measurement procedures" Paragraph 1; "In this study, the PPG waveform was measured by a validated medical pulse oximeter (BM2000A from Shanghai Berry Electronic Technology Co., Ltd), with a modified receiving protocol to record raw data." Xiaoman Section "PPG and BP measurement procedures" Paragraph 3;"The purpose of this study is to collect as many data as possible to build a best-performing model, and evaluate its applicability. It’s not meant to validate a specific BP measuring device or algorithm, so we did not follow the standard validation procedure for BP measuring devices" Examiner notes that plurality of digital signal data is received/receiving protocol to record raw data from at least one sensor device/medical pulse oximeter of a plurality of sensor devices/Paragraph 3 suggests multiple measuring devices used; medical pulse oximeter contains a processor and receives data)
Dynamically (Xiaoman Section "Discussion" Paragraph 1; "This technological breakthrough helps us make extremely small, comfortable, noninvasive and inexpensive devices, which will facilitate its widespread application in continuous BP monitoring and cardiovascular health management." Examiner notes that continuous BP monitoring means dynamic processing)
Xiaoman does not teach [dynamically] convert at least one digital [PPG] sample of the plurality of digital [PPG] samples into at least one visibility node in a plurality of visibility nodes based on a plurality of time series vectors associated with the plurality of digital [PPG] samples;
Determine a visibility graph comprising a plurality of visibility edges amongst the plurality of visibility nodes based at least in part on a visibility between each visibility node of a plurality of candidate visibility node pairs;
Generate utilizing the plurality of visibility nodes and the plurality of visibility edges, at least one image to represent visibility graph of the plurality of time series vector associated with the time window of the digital [PPG] signal data,
However, Lucas does teach [dynamically] convert at least one digital [PPG] sample of the plurality of digital [PPG] samples into at least one visibility node in a plurality of visibility nodes based on a plurality of time series vectors associated with the plurality of digital [PPG] samples; (Lucas “Resumen”; “In this work we present a simple and fast computational method, the visibility algorithm” Lucas Page 1 Paragraph 2; "we plot the first twenty values of a periodic series using vertical bars (the data values are displayed above the plot). Considering this as a landscape, we link every bar (every point of the time series) with all those that can be seen from the top of the considered one (gray lines)" Examiner notes that at least one digital PPG sample of the plurality of PPG sample/first twenty values are converted into at least one visibility node/node at the top of bar in a plurality of visibility node/every point on each bar based a plurality of time series vectors/every bar of every point associated with the plurality of PPG samples/converted from signal data; the algorithm is a computational method meaning a processor performs the algorithm)
Determine a visibility graph comprising a plurality of visibility edges amongst the plurality of visibility nodes based at least in part on a visibility between each visibility node of a plurality of candidate visibility node pairs; (Lucas Paragraph 2; “we present a scheme of the visibility algorithm. In the upper zone we plot the first twenty values of a periodic series using vertical bars (the data values are displayed above the plot). Considering this as a landscape, we link every bar (every point of the time series) with all those that can be seen from the top of the considered one (gray lines), obtaining the associated graph (shown in the lower part of the figure). In this graph, every node corresponds, in the same order, to a series data, and two nodes are connected if there exists visibility between the corresponding data, that is to say, if there is a straight line that connects the series data, provided that this “visibility line” does not intersect any intermediate data height. More formally, we can establish the following visibility criterium: two arbitrary” Examiner notes that a visibility graph (associated graph (shown in the lower part of the figure)) is determined, by the visibility algorithm, comprising a plurality of visibility edges (visibility line) amongst the plurality of visibility nodes (every point/node on top each bar) based at least in part on a visibility between each visibility node of a plurality of candidate visibility node pairs (every node corresponds, in the same order, to a series data, and two nodes are connected if there exists visibility between the corresponding data, that is to say, if there is a straight line that connects the series data, provided that this “visibility line” does not intersect any intermediate data height))
Generate utilizing the plurality of visibility nodes and the plurality of visibility edges, at least one image to represent visibility graph of the plurality of time series vector associated with the time window of the digital [PPG] signal data,; (Lucas Page 1 Paragraph 2; "we link every bar (every point of the time series) with all those that can be seen from the top of the considered one (gray lines), obtaining the associated graph (shown in the lower part of the figure). " Lucas Page 10 Figure 2; "The visibility graph of a time series remains invariant under several transformation of the time series" Examiner notes that utilizing the plurality of visibility nodes (every point of the time series) and the plurality of visibility edges (link every bar with those that can be seen from the top), generating/obtaining at least one image/associated graph to represent the visibility graph (visibility graph of a time series) of the plurality of time series vectors (bar for every point) associated with the time window of the digital signal data (time window of first 20 values); time series vectors are represented as lines and lines are a 2d shape)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Xiaoman and Lucas. Xiaoman teaches a novel paradigm to unobtrusively and optically measure blood pressure (BP) without calibration.. Lucas teaches converting time series data into visibility graphs. One of ordinary skill would have motivation to combine Xiaoman and Lucas to convert the time blood pressure data into visibility graphs to reveal non trivial information about the data “this network inherits several properties of the time series, and its study reveals non trivial information about the series itself.” (Lucas Page 1 Paragraph 1).
Xiaoman in view of Lucas does not teach A system for cuff-less blood pressure estimation from digital photoplethysmography (PPG) signal data, the system comprising: at least one processor configured to execute software instructions, wherein the software instructions, when executed, cause the at least one processor to perform steps to:
Extract using a pre-trained image analysis machine learning model, at least one feature metric of a plurality of feature metrics from the at least one image
and at least one pre-trained relation between the at least one feature metric and the at least one image wherein the at least one pre-trained relation comprises at least one weight, at least one bias, or both
based at least in part on: the at least one prior feature metric extracted from at least one prior [visibility] graph, [and the at least one reference blood pressure].
However, Randy does teach extract using a pre-trained image analysis machine learning model, at least one feature metric of a plurality of feature metrics from the at least one image (Randy Column 9 Paragraph 2; "The convolution operations in a CNN may be used to extract features from input image 310." Randy Column 24 Paragraph 3; "a general purpose computer with instruction code, or a computing system as described below with respect to FIG. 12. The instruction code may be stored on a non-transitory storage medium (e.g., on a memory device)." Examiner notes that CNN/pre-trained machine learning algorithm is used to analyze the image and extract at least one feature metric of a plurality of feature metrics/features from the at least one image/input image; method includes processor that executes instruction code for extraction and following claimed functions)
and at least one pre-trained relation between the at least one feature metric and the at least one image wherein the at least one pre-trained relation comprises at least one weight, at least one bias, or both (Randy Column 10 Paragraph 4; “a CNN may learn the weights of the filters on its own during the training process based on some user specified parameters (which may be referred to as hyperparameters) before the training process, such as the number of filters, the filter size, the architecture of the network, etc. The more number of filters used, the more image features may get extracted, and the better the network may be at recognizing patterns in new images.” Examiner notes that the at least one pre-trained relation (CNN may learn the weights of the filters on its own during the training process) between the at least one feature metric (image features) and the at least one image (new images) wherein the at least one pre-trained relation comprises at least one weight (CNN may learn weights); being based on the feature metric is also based on the relation between the feature metric and image because the feature metric is extracted from the image)
based at least in part on: the at least one prior feature metric extracted from at least one prior [visibility] graph, [and the at least one reference blood pressure]. (Randy Column 13 Paragraph 2; “use the gradient descent to update parameters and weights to be trained in the network to minimize the output error… When the same training sample is input again, the output probabilities might be closer to the target probabilities, which indicates that the network has learned to classify this particular image.” Examiner notes that the weights is based at least in part on the at least one prior feature metric (output probabilities of previous training) extracted from at least one prior graph (particular image))
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Xiaoman, Lucas, and Randy. Xiaoman teaches a novel paradigm to unobtrusively and optically measure blood pressure (BP) without calibration.. Lucas teaches converting time series data into visibility graphs. Randy teaches the use of artificial neural networks to classify objects in an image. One of ordinary skill would have motivation to combine Xiaoman, Lucas, and Randy to leverage artificial neural network capabilities in the medical field “An artificial neural network (ANN) is a computational system that is inspired by the way biological neural networks in the human brain process information. Artificial neural networks have been used in machine learning research and industrial applications and have achieved many breakthrough results in, for example, image recognition, speech recognition, computer vision, text processing, etc.” (Randy Column 4 Paragraph 1).
Xiaoman in view of Lucas in further view of Randy does not teach and generate utilizing a regression algorithm, at least one blood pressure estimation associated with the time window based at least in part on the at least one feature metric,
[and at least one pre-trained relation between the at least one feature metric and the at least one image] wherein the at least one pre-trained relation comprises at least one weight, at least one bias, or both based at least in part on: [the at least one prior feature metric extracted from at least one prior visibility graph, and] the at least one reference blood pressure
However, Schmitt does teach and generate utilizing a regression algorithm, at least one blood pressure estimation associated with the time window based at least in part on the at least one feature metric, (Schmitt Paragraph 0018; “a non-transitory computer-readable recording medium that stores therein a computer program product, which, when executed by a processor, causes the method disclosed herein to be performed.” Schmitt Paragraph 0025; “Features that show good correlation with blood pressure may be selected and for each selected feature a blood pressure estimation value can be calculated (e.g. via regression according to a mathematical model, using again the blood pressure reference measurements).” Schmitt Paragraph 0057; “The selection of features is based on functions that can be applied to the PPG waveform signal and provide a feature value. As an example, the feature time_deri2a (time from maximum of first derivate to minimum of dicrotic notch)” Examiner notes that processor executes the step of utilizing a regression algorithm (via regression according to a mathematical model) to generate at least one blood pressure estimation (blood pressure estimation value) associated with the time window (time from maximum of first derivate to minimum of dicrotic notch) is based at least in part on the at least one feature metric (feature that show good correlation))
[and at least one pre-trained relation between the at least one feature metric and the at least one image] wherein the at least one pre-trained relation comprises at least one weight, at least one bias, or both based at least in part on: [the at least one prior feature metric extracted from at least one prior visibility graph, and] the at least one reference blood pressure (Schmitt Paragraph 0025; “Preferably, the estimation unit is configured to determine the subject's blood pressure by taking a weighted average of some or all of said multiple blood pressure estimation values, wherein said weights used for said weighted average are determined based on a correlation between a subject's blood pressure and its corresponding feature” Examiner notes that the weights are based at least in part of the at least one reference blood pressure (subject’s blood pressure))
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Xiaoman, Lucas, Randy, and Schmitt. Xiaoman teaches a novel paradigm to unobtrusively and optically measure blood pressure (BP) without calibration. Lucas teaches converting time series data into visibility graphs. Randy teaches the use of artificial neural networks to classify objects in an image. Schmitt teaches method for determining blood pressure of a subject. One of ordinary skill would have motivation to combine Xiaoman, Lucas, Randy, and Schmitt to improve the feature selection process “the feature selection process can be improved by utilizing the signal-to-noise ratio of the measured features. For example, if the signal-to-noise ratio of the measured features is low, then the measured correlation coefficient or the measured regression error can be penalized by proper weighting factors.” (Schmitt Paragraph 0071).
Regarding claim 12, Xiaoman teaches The system of claim 11, wherein the plurality of digital signal data comprises a plurality of physiological data signals. (Xiaoman Section "PPG and BP measurement procedure" Paragraph 1; "In this study, the PPG waveform was measured by a validated medical pulse oximeter")
Regarding claim 13, Xiaoman does not teach The system of claim 11, wherein the plurality of visibility nodes preserves a plurality of temporal information associated with a data waveform based on the plurality of digital signal data.
However, Lucas does teach The system of claim 11, wherein the plurality of visibility nodes preserves a plurality of temporal information associated with a data waveform based on the plurality of digital signal data. Lucas Page 2 Paragraph 3; "In the case of periodic time series, its regularity seems therefore to be conserved or inherited structurally in the graph by means of the visibility map." Examiner notes that the plurality of visibility node in the visibility map preserves a plurality of temporal information/regularity is conserved or inherited structurally associated with a data waveform/structure of graph based on the plurality of digital signal data)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Xiaoman and Lucas. Xiaoman teaches a novel paradigm to unobtrusively and optically measure blood pressure (BP) without calibration.. Lucas teaches converting time series data into visibility graphs. One of ordinary skill would have motivation to combine Xiaoman and Lucas to convert the time blood pressure data into visibility graphs to reveal non trivial information about the data “this network inherits several properties of the time series, and its study reveals non trivial information about the series itself.” (Lucas Page 1 Paragraph 1).
Regarding claim 14, Xiaoman does not teach The system of claim 11, wherein the pre-trained machine learning algorithm comprises a deep conventional neural network.
However, Randy does teach The system of claim 11, wherein the pre-trained machine learning algorithm comprises a deep conventional neural network. (Randy Column 7 Paragraph 5; "LeNet developed by Yann LeCun et al. in 1990s for hand-written number recognition is one of the first convolutional neural networks that helped propel the field of deep learning." Examiner notes that CNN/pre-trained machine learning algorithm comprises/is a deep conventional neural network)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Xiaoman, Lucas, and Randy. Xiaoman teaches a novel paradigm to unobtrusively and optically measure blood pressure (BP) without calibration.. Lucas teaches converting time series data into visibility graphs. Randy teaches the use of artificial neural networks to classify objects in an image. One of ordinary skill would have motivation to combine Xiaoman, Lucas, and Randy to leverage artificial neural network capabilities in the medical field “An artificial neural network (ANN) is a computational system that is inspired by the way biological neural networks in the human brain process information. Artificial neural networks have been used in machine learning research and industrial applications and have achieved many breakthrough results in, for example, image recognition, speech recognition, computer vision, text processing, etc.” (Randy Column 4 Paragraph 1).
Regarding claim 16, Xiaoman does not teach The system of claim 11, wherein the pre-trained learning algorithm is one of AlexNet, VGG-19 or Inception v3.
However, Randy does teach The system of claim 11, wherein the pre-trained learning algorithm is one of AlexNet, VGG-19 or Inception v3. (Randy Column 13 Paragraph 4; "There may be many variations and improvements to CNN 300 described above, such as AlexNet")
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Xiaoman, Lucas, and Randy. Xiaoman teaches a novel paradigm to unobtrusively and optically measure blood pressure (BP) without calibration.. Lucas teaches converting time series data into visibility graphs. Randy teaches the use of artificial neural networks to classify objects in an image. One of ordinary skill would have motivation to combine Xiaoman, Lucas, and Randy to leverage artificial neural network capabilities in the medical field “An artificial neural network (ANN) is a computational system that is inspired by the way biological neural networks in the human brain process information. Artificial neural networks have been used in machine learning research and industrial applications and have achieved many breakthrough results in, for example, image recognition, speech recognition, computer vision, text processing, etc.” (Randy Column 4 Paragraph 1).
Regarding claim 17, Xiaoman teaches The system of claim 11, wherein the plurality of digital signal data comprises PPG data and reference BP data. (Xiaoman Section "PPG and BP measurement procedure" shows that plurality of digital signal data is/comprises PPG data and reference BP data)
Regarding claim 18, Xiaoman does not teach The system of claim 11, wherein the at least one image is a visibility graph (VG).
However, Lucas does teach The system of claim 11, wherein the at least one image is a visibility graph (VG). (Lucas Page 9 Figure 1 shows that image is a visibility graph)
PNG
media_image1.png
375
614
media_image1.png
Greyscale
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Xiaoman and Lucas. Xiaoman teaches a novel paradigm to unobtrusively and optically measure blood pressure (BP) without calibration.. Lucas teaches converting time series data into visibility graphs. One of ordinary skill would have motivation to combine Xiaoman and Lucas to convert the time blood pressure data into visibility graphs to reveal non trivial information about the data “this network inherits several properties of the time series, and its study reveals non trivial information about the series itself.” (Lucas Page 1 Paragraph 1).
Regarding claim 19, Xiaoman teaches The system of claim 11, wherein the software instructions, when executed, further cause the at least one processor to perform steps to: apply a selection procedure to the plurality of digital signal data to remove at least one of: duplicated digital signal data, at least one error in the digital PPG signal data, or digital signal with less than a predetermined number of systolic peaks. (Xiaoman Section "Data Selection" Paragraph 1; "If one feature from a particular beat was considered an outlier, this particular beat was labeled abnormal and discarded. If the percentage of abnormal beats for a measurement exceeded 20%, the entire measurement was excluded.")
Regarding claim 20, Xiaoman does not teach The system of claim 11, wherein the software instructions, when executed, further cause the at least one processor to perform steps to classify the feature metric into one of at least two classes.
However, Randy does teach The system of claim 11, wherein the software instructions, when executed, further cause the at least one processor to perform steps to classify the feature metric into one of at least two classes. (Randy Column 12 Paragraph 3; "Fully-connected layer 360 may use the high-level features of the input image represented by output matrices 350 to classify the input image into various classes based on the training dataset." Examiner notes that the feature metric/features are being classified into one of at least two classes/various classes)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Xiaoman, Lucas, and Randy. Xiaoman teaches a novel paradigm to unobtrusively and optically measure blood pressure (BP) without calibration.. Lucas teaches converting time series data into visibility graphs. Randy teaches the use of artificial neural networks to classify objects in an image. One of ordinary skill would have motivation to combine Xiaoman, Lucas, and Randy to leverage artificial neural network capabilities in the medical field “An artificial neural network (ANN) is a computational system that is inspired by the way biological neural networks in the human brain process information. Artificial neural networks have been used in machine learning research and industrial applications and have achieved many breakthrough results in, for example, image recognition, speech recognition, computer vision, text processing, etc.” (Randy Column 4 Paragraph 1).
Claim(s) 21 and 22 are rejected under 35 U.S.C. 103 as being unpatentable over Xiaoman et al; “An Unobtrusive and Calibration-free Blood Pressure Estimation Method using Photoplethysmography and Biometrics” (hereinafter “Xiaoman”) in view of Lucas et al; “From time series to complex networks: the visibility graph” (hereinafter “Lucas”) in further view of Randy et al; US 11868878 B1 (hereinafter “Randy”) in further view of Lars Schmitt et al; US 20200229716 A1 (hereinafter “Schmitt”) in further view of Sophia Miryam Schussler-Fiorenza et al; US 20200227166 A1 (hereinafter “Sophia”
Regarding claim 21, Xiaoman teaches digital PPG signal data and paired reference blood values (Xiaoman Fig 3 and Section "PPG and BP measurement procedures" Paragraph 1; "In this study, the PPG waveform was measured by a validated medical pulse oximeter (BM2000A from Shanghai Berry Electronic Technology Co., Ltd), with a modified receiving protocol to record raw data” Examiner notes that digital PPG signal data is raw data and paired reference blood values is systolic peak and dicrotic notch of the PPG waveform; this data is)
PNG
media_image2.png
274
580
media_image2.png
Greyscale
Xiaoman does not teach The method of claim 1, wherein the regression algorithm is trained by: applying ridge regression or model fine-tuning or both to the at least one prior feature metric extracted from the at least one prior visibility graph generated from the at least one prior digital PPG signal data and paired reference blood pressure values, and the at least one pre-trained relation between the at least one feature metric and the at least one image, to solve for the at least one weight, the at least one bias, or both.
However, Lucas does teach visibility graph generated from the at least one prior digital [PPG] signal data and paired reference [blood pressure] values (Lucas Paragraph 2; “we present a scheme of the visibility algorithm. In the upper zone we plot the first twenty values of a periodic series using vertical bars (the data values are displayed above the plot). Considering this as a landscape, we link every bar (every point of the time series) with all those that can be seen from the top of the considered one (gray lines), obtaining the associated graph (shown in the lower part of the figure). In this graph, every node corresponds, in the same order, to a series data, and two nodes are connected if there exists visibility between the corresponding data, that is to say, if there is a straight line that connects the series data, provided that this “visibility line” does not intersect any intermediate data height. More formally, we can establish the following visibility criterium: two arbitrary” Examiner notes that visibility graph is generated from the at least one prior digital signal data (first twenty values of a periodic series) and paired reference values (two nodes are connected if there exists visibility between the corresponding data))
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Xiaoman and Lucas. Xiaoman teaches a novel paradigm to unobtrusively and optically measure blood pressure (BP) without calibration.. Lucas teaches converting time series data into visibility graphs. One of ordinary skill would have motivation to combine Xiaoman and Lucas to convert the time blood pressure data into visibility graphs to reveal non trivial information about the data “this network inherits several properties of the time series, and its study reveals non trivial information about the series itself.” (Lucas Page 1 Paragraph 1).
Xiaoman in view of Lucas does not teach prior feature metric extracted from the at least one prior [visibility] graph [generated from the at least one prior digital PPG signal data and paired reference blood pressure values, and the at least one pre-trained relation between the at least one feature metric and the at least one image,]
and the at least one pre-trained relation between the at least one feature metric and the at least one image,
However, Randy does teach prior feature metric extracted from the at least one prior [visibility] graph [generated from the at least one prior digital PPG signal data and paired reference blood pressure values, and the at least one pre-trained relation between the at least one feature metric and the at least one image,] (Randy Column 9 Paragraph 2; "The convolution operations in a CNN may be used to extract features from input image 310." Examiner notes that prior feature metric (features) is extracted from the at least one prior graph (input image))
and the at least one pre-trained relation between the at least one feature metric and the at least one image, (Randy Column 10 Paragraph 4; “a CNN may learn the weights of the filters on its own during the training process based on some user specified parameters (which may be referred to as hyperparameters) before the training process, such as the number of filters, the filter size, the architecture of the network, etc. The more number of filters used, the more image features may get extracted, and the better the network may be at recognizing patterns in new images.” Examiner notes that the relation is pre-trained (training of CNN) between the at least one feature metric (image features) and the at least one image (new images)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Xiaoman, Lucas, and Randy. Xiaoman teaches a novel paradigm to unobtrusively and optically measure blood pressure (BP) without calibration.. Lucas teaches converting time series data into visibility graphs. Randy teaches the use of artificial neural networks to classify objects in an image. One of ordinary skill would have motivation to combine Xiaoman, Lucas, and Randy to leverage artificial neural network capabilities in the medical field “An artificial neural network (ANN) is a computational system that is inspired by the way biological neural networks in the human brain process information. Artificial neural networks have been used in machine learning research and industrial applications and have achieved many breakthrough results in, for example, image recognition, speech recognition, computer vision, text processing, etc.” (Randy Column 4 Paragraph 1).
The method of claim 1, wherein the regression algorithm is trained by: applying ridge regression or model fine-tuning or both to the at least one prior feature metric [extracted from the at least one prior visibility graph generated from the at least one prior digital PPG signal data and paired reference blood pressure values, and the at least one pre-trained relation between the at least one feature metric and the at least one image,] to solve for the at least one weight, the at least one bias, or both. (Sophia Paragraph 0155; “Ridge regression attempts to find the best set of weights to combine the features for glycemic regulation determination” Examiner notes that the regression algorithm is trained by: applying ridge regression (ridge regression attempts) to the at least one prior feature metric (features for glycemic regulation determination) to solve for the at least one weight (find best set of weights))
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Xiaoman, Lucas, Randy, Schmitt, and Sophia. Xiaoman teaches a novel paradigm to unobtrusively and optically measure blood pressure (BP) without calibration. Lucas teaches converting time series data into visibility graphs. Randy teaches the use of artificial neural networks to classify objects in an image. Schmitt teaches method for determining blood pressure of a subject. Sophia teaches ridge regression. One of ordinary skill would have motivation to combine Xiaoman, Lucas, Randy, and Schmitt to reduce the standard errors and make estimates more reliable “a ridge regression technique can reduce these variances to better reach the true value. Ridge regression adds a degree of bias to the regression estimates, and thus reduces the standard errors, which should result in estimates that are more reliable.” (Sophia Paragraph 0154).
Regarding claim 22, Xiaoman teaches digital PPG signal data and paired reference blood values (Xiaoman Fig 3 and Section "PPG and BP measurement procedures" Paragraph 1; "In this study, the PPG waveform was measured by a validated medical pulse oximeter (BM2000A from Shanghai Berry Electronic Technology Co., Ltd), with a modified receiving protocol to record raw data” Examiner notes that digital PPG signal data is raw data and paired reference blood values is systolic peak and dicrotic notch of the PPG waveform; this data is)
PNG
media_image2.png
274
580
media_image2.png
Greyscale
Xiaoman does not teach The system of claim 11, wherein the regression algorithm is trained by: applying ridge regression or model fine-tuning or both to the at least one prior feature metric extracted from the at least one prior visibility graph generated from the at least one prior digital PPG signal data and paired reference blood pressure values, and the at least one pre-trained relation between the at least one feature metric and the at least one image, to solve for the at least one weight, the at least one bias, or both.
However, Lucas does teach visibility graph generated from the at least one prior digital [PPG] signal data and paired reference [blood pressure] values (Lucas Paragraph 2; “we present a scheme of the visibility algorithm. In the upper zone we plot the first twenty values of a periodic series using vertical bars (the data values are displayed above the plot). Considering this as a landscape, we link every bar (every point of the time series) with all those that can be seen from the top of the considered one (gray lines), obtaining the associated graph (shown in the lower part of the figure). In this graph, every node corresponds, in the same order, to a series data, and two nodes are connected if there exists visibility between the corresponding data, that is to say, if there is a straight line that connects the series data, provided that this “visibility line” does not intersect any intermediate data height. More formally, we can establish the following visibility criterium: two arbitrary” Examiner notes that visibility graph is generated from the at least one prior digital signal data (first twenty values of a periodic series) and paired reference values (two nodes are connected if there exists visibility between the corresponding data))
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Xiaoman and Lucas. Xiaoman teaches a novel paradigm to unobtrusively and optically measure blood pressure (BP) without calibration.. Lucas teaches converting time series data into visibility graphs. One of ordinary skill would have motivation to combine Xiaoman and Lucas to convert the time blood pressure data into visibility graphs to reveal non trivial information about the data “this network inherits several properties of the time series, and its study reveals non trivial information about the series itself.” (Lucas Page 1 Paragraph 1).
Xiaoman in view of Lucas does not teach prior feature metric extracted from the at least one prior [visibility] graph [generated from the at least one prior digital PPG signal data and paired reference blood pressure values, and the at least one pre-trained relation between the at least one feature metric and the at least one image,]
and the at least one pre-trained relation between the at least one feature metric and the at least one image,
However, Randy does teach prior feature metric extracted from the at least one prior [visibility] graph [generated from the at least one prior digital PPG signal data and paired reference blood pressure values, and the at least one pre-trained relation between the at least one feature metric and the at least one image,] (Randy Column 9 Paragraph 2; "The convolution operations in a CNN may be used to extract features from input image 310." Examiner notes that prior feature metric (features) is extracted from the at least one prior graph (input image))
and the at least one pre-trained relation between the at least one feature metric and the at least one image, (Randy Column 10 Paragraph 4; “a CNN may learn the weights of the filters on its own during the training process based on some user specified parameters (which may be referred to as hyperparameters) before the training process, such as the number of filters, the filter size, the architecture of the network, etc. The more number of filters used, the more image features may get extracted, and the better the network may be at recognizing patterns in new images.” Examiner notes that the relation is pre-trained (training of CNN) between the at least one feature metric (image features) and the at least one image (new images)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Xiaoman, Lucas, and Randy. Xiaoman teaches a novel paradigm to unobtrusively and optically measure blood pressure (BP) without calibration.. Lucas teaches converting time series data into visibility graphs. Randy teaches the use of artificial neural networks to classify objects in an image. One of ordinary skill would have motivation to combine Xiaoman, Lucas, and Randy to leverage artificial neural network capabilities in the medical field “An artificial neural network (ANN) is a computational system that is inspired by the way biological neural networks in the human brain process information. Artificial neural networks have been used in machine learning research and industrial applications and have achieved many breakthrough results in, for example, image recognition, speech recognition, computer vision, text processing, etc.” (Randy Column 4 Paragraph 1).
The method of claim 1, wherein the regression algorithm is trained by: applying ridge regression or model fine-tuning or both to the at least one prior feature metric [extracted from the at least one prior visibility graph generated from the at least one prior digital PPG signal data and paired reference blood pressure values, and the at least one pre-trained relation between the at least one feature metric and the at least one image,] to solve for the at least one weight, the at least one bias, or both. (Sophia Paragraph 0155; “Ridge regression attempts to find the best set of weights to combine the features for glycemic regulation determination” Examiner notes that the regression algorithm is trained by: applying ridge regression (ridge regression attempts) to the at least one prior feature metric (features for glycemic regulation determination) to solve for the at least one weight (find best set of weights))
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Xiaoman, Lucas, Randy, Schmitt, and Sophia. Xiaoman teaches a novel paradigm to unobtrusively and optically measure blood pressure (BP) without calibration. Lucas teaches converting time series data into visibility graphs. Randy teaches the use of artificial neural networks to classify objects in an image. Schmitt teaches method for determining blood pressure of a subject. Sophia teaches ridge regression. One of ordinary skill would have motivation to combine Xiaoman, Lucas, Randy, and Schmitt to reduce the standard errors and make estimates more reliable “a ridge regression technique can reduce these variances to better reach the true value. Ridge regression adds a degree of bias to the regression estimates, and thus reduces the standard errors, which should result in estimates that are more reliable.” (Sophia Paragraph 0154).
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to DANIEL DUC TRAN whose telephone number is (571)272-6870. The examiner can normally be reached Mon-Fri 8:00-5:00 EST.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Viker Lamardo can be reached at (571) 270-5871. 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.
/D.D.T./Examiner, Art Unit 2147
/ERIC NILSSON/Primary Examiner, Art Unit 2151
Prosecution Insights