DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Status of the Claims
Claims 1-20 are pending and examined herein. No claims are canceled.
Priority
As detailed on the 29 March 2022 filing receipt, the application claims priority as early as 29 March 2021. At this point in examination, all claims have been interpreted as being accorded this priority date as the effective filing date.
Specification
The title of the specification is objected to because it lists items without separations by commas. The following title is suggested: METHODS, CIRCUITS, DEVICES, SYSTEMS, AND MACHINE EXECUTABLE CODE FOR GLUCOSE EVENT DETECTION.
Claim Objections
Claim 3 is objected to because of the following informalities: the claim recites “comprising a a photoplethysmogram” and thus one article requires deletion. Appropriate correction is required.
Claim Rejections - 35 USC § 112(b)
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 3-6 is rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
The term “the timestamped variable BPM input streams” occurs in claim 3 but the recited term is not previously instantiated. Therefore, the timestamped variable BPM input streams lack antecedence and render the claim unclear. Claims 4-6 are dependent on claim 3 and do not remedy this lack of clarity and thus are rejected on similar grounds.
The term “higher than normal” in claim 6 is a relative term which renders the claim indefinite. The terms “higher” and “normal” are not defined by the claim, the specification does not provide a standard for ascertaining the requisite degree, and one of ordinary skill in the art would not be reasonably apprised of the scope of the invention. While the claims and specification disclose an incongruence between the blood glucose level output of the model overlapping with physical activity as indicated by the accelerometer, the metric for what is “normal” and how much above normal qualifies as “higher” are not disclosed, thus rendering the claim indefinite.
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 1-2 and 7-17 are rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter. The claim(s) does/do not fall within at least one of the four categories of patent eligible subject matter. Claim 1 recites a detection system comprising “an artificial recurrent neural network” but the neural network is not recited as associated with a physical structure such as a computer and thus is interpreted as data per se. Similarly, claim 2 recites a “computer readable medium” which may be non-transitory and thus is interpreted as software per se. While a continuous glucose monitor is recited in claim 2, which is not software or data, it is not clearly part of the glucose event detection system. The data analyzed by the neural network is generated by the CGM but the CGM may not be part of the system. Thus, claim 2 and its dependents – claims 7-17 – are rejected as not directed to statutory subject matter. Amendment to recite specific hardware or other elements in addition to the abstract ideas in independent claim 1 and dependent claims 2 and 7-17 may overcome this rejection.
Claims 1-2 and 19-20 are rejected under 35 USC § 101 because the claimed inventions are directed to an abstract idea without significantly more. "Claims directed to nothing more than abstract ideas (such as a mathematical formula or equation), natural phenomena, and laws of nature are not eligible for patent protection" (MPEP 2106.04 § I). Abstract ideas include mathematical concepts, and procedures for evaluating, analyzing or organizing information, which are a type of mental process (MPEP 2106.04(a)(2)). The claims as a whole, considering all claim elements both individually and in combination, do not amount to significantly more than the abstract idea of generating a predicted blood glucose level.
MPEP 2106 organizes JE analysis into Steps 1, 2A (Prong One & Prong Two), and 2B as analyzed below.
Step 1: Are the claims directed to a process, machine, manufacture, or composition of matter (MPEP 2106.03)?
Step 2A, Prong One: Do the claims recite a judicially recognized exception, i.e., a law of
nature, a natural phenomenon, or an abstract idea (MPEP 2106.04(a-c))?
Step 2A, Prong Two: If the claims recite a judicial exception under Prong One, then is the judicial exception integrated into a practical application by an additional element (MPEP 2106.04(d))?
Step 2B: Do the claims recite a non-conventional arrangement of elements in addition to any identified judicial exception(s) (MPEP 2106.05)?
Step 1: Are the claims directed to a 101 process, machine, manufacture, or composition of matter (MPEP 2106.03)?
The claims are directed to a computer system (claims 1-2) and a method (claims 19-20), each of which falls within one of the categories of statutory subject matter. [Step 1: Yes]
Step 2A, Prong One: Do the claims recite a judicially recognized exception, i.e., a law of nature, a natural phenomenon, or an abstract idea (MPEP 2106.04(a-c))?
With respect to Step 2A, Prong One, the claims recite judicial exceptions in the form of abstract ideas. MPEP § 2106.04(a)(2) further explains that abstract ideas are defined as:
• mathematical concepts (mathematical formulas or equations, mathematical relationships
and mathematical calculations) (MPEP 2106.04(a)(2)(I));
• certain methods of organizing human activity (fundamental economic principles or practices, managing personal behavior or relationships or interactions between people) (MPEP 2106.04(a)(2)(II)); and/or
• mental processes (concepts practically performed in the human mind, including observations, evaluations, judgments, and opinions) (MPEP 2106.04(a)(2)(III)).
Mathematical concepts recited in claims 1 and 19 include generating blood glucose level output. The specification discloses the prediction of blood glucose level requires input of a vector comprising a time series of heart beats per minute and outputs a vector of blood glucose levels (pg. 11, paragraph [52]), and thus it is interpreted that a mathematical process is occurring.
Claims 2 and 20 recite feeding data into a model, which is a mathematical concept. Claims 2 and 20 recite applying a loss function and updating the model based on the results of the loss function, where a loss function and updating a model are both interpreted as mathematical concepts.
Hence, the claims explicitly recite numerous elements that, individually and in combination,
constitute abstract ideas. The claims must therefore be examined further to determine whether they
integrate that abstract idea into a practical application (MPEP 2106.04(d)). [Step 2A: Yes]
Step 2A, Prong Two: If the claims recite a judicial exception under Prong One, then is the judicial exception integrated into a practical application by an additional element (MPEP 2106.04(d))?
Claims 1 and 19 recite an additional element that is not an abstract ideas: a recurrent neural network architecture of long short-term memory cells.
Claim 2 recites a computer readable medium, interpreted as memory.
Using the recurrent neural network of long short-term memory cells and memory is interpreted as implementing the abstract idea of generating blood glucose level on a computer (MPEP 2106.05(f)). The RNN is a tool to perform the process, which does not integrate the abstract idea into a practical application. [Step 2A Prong Two: No]
Step 2B: Do the claims recite a non-conventional arrangement of elements in addition to any identified judicial exception(s) (MPEP 2106.05)?
Claims found to be directed to a judicial exception are then further evaluated to determine if the claims recite an inventive concept that provides significantly more than the judicial exception itself. Step 2B of 101 analysis determines whether the claims contain additional elements that amount to an inventive concept, and an inventive concept cannot be furnished by an abstract idea itself (MPEP 2106.05). Frank (US 20210007607 A1; newly cited) teaches at least an RNN with LSTM architecture for detecting blood glucose levels (pg. 15, paragraph [155]) and a computer readable medium (pg. 68, paragraph [640]); Dalal (US 20200176121 A1; newly cited) teaches RNN with LSTM associated with continuous glucose monitoring (paragraphs [108-109]) and a computer readable medium (paragraph [42]); and Dong (CN 107203700 A; newly cited) teaches a CGM device associated with an LSTM RNN (pg. 4, paragraphs 2-4). Therefore, the above recited additional elements, alone or in combination with the judicial exceptions, do not appear to provide an inventive concept. [Step 2B: No]
Conclusion: Claims are Directed to Non-statutory Subject Matter
For these reasons, the above considered claims, when the limitations are considered individually and as a whole, are directed to an abstract idea and lack an inventive concept. Hence, the claimed invention does not constitute significantly more than the abstract idea, so the claims are rejected under 35 USC § 101 as being directed to non-statutory subject matter.
It is noted that the use of a continuous glucose monitor, photoplethysmogram device, and the nuances of the RNN LSTM architecture are not conventionally found together in the prior art, and so claims 3-17 are not rejection under 35 USC 101.
Claim Rejections - 35 USC § 102
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 the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
The text of those sections of Title 35, U.S. Code not included in this action can be found in a prior Office action.
Claims 1 and 19 are rejected under 35 U.S.C. 102(a)(1) and 102(a)(2) as being anticipated by Frank (US 20210007607 A1; newly cited).
Claim 1 recites a glucose event detection system, comprising an artificial recurrent neural network (RNN) architecture of long short-term memory (LSTM) cells, configured to generate, for a monitored subject, variable blood glucose level (BGL) output streams predictions for respective, system fed, variable heart beats per minute (BPM) input streams of the monitored subject.
Frank teaches a non-invasive manner of calculating blood glucose level, where variation in heartbeat changes as a function of blood glucose level as detected by photoplethysmography (pg. 2, paragraph [7]). Frank teaches a method involving a recurrent neural network implemented using long short-term memory architecture (pg. 15, paragraph [155]).
Claim 19 recites a method comprising the limitations of system claim 1.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 2-4, 7-10, 16-17, and 20
Claims 2-4, 7-10, 16-17, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Frank as applied to claims 1 and 19 above and further in view of Bidet (US 2021/0068669 A1; newly cited).
Claim 2 recites a computer readable medium including instructions for a supervised training mechanism for, iteratively: (1) feeding to said artificial RNN architecture model, as input data, variable BPM input streams of the monitored subject, for the model to generate corresponding variable BGL model output streams predictions; (2) applying a loss function for measuring the "error" in the model's BGL output streams predictions, relative to time-aligned and labeled variable BGL output streams from a continuous blood glucose monitoring (CGM) device concurrently monitoring the subject; and (3) updating weight values of said RNN model based on said loss function measured "error", to gradually
reduce that error.
Frank teaches instructions stored on a compute readable medium (pg. 16, paragraph [157]). Frank teaches blood flow changes obtained from a PPG device (pg. 5, paragraph [72]), where beats per minute is interpreted as reading on blood flow changes. Frank teaches the PPG signal as input into the computer device, which includes an RNN, to determine blood glucose (Fig. 1a).
Frank does not teach applying a loss function relative to the blood glucose level output from a CGM or updating weight values based on measured error from the loss function.
Bidet teaches a method for predicting glycemia including generating data from a CGM (pg. 1, paragraph [22]) into a neural network, in which “a loss function is used to calculate the difference between the network output and its expected output” (paragraph [352]), where error reads on such a difference, and “backpropagation uses these error values to calculate the gradient of the loss function. This gradient is then fed to an optimization algorithm which updates weights, in attempt to minimize the loss function” (paragraph [354]).
Claim 20 recites a method comprising the limitations of system claim 2.
Claim 3 recites a photoplethysmogram (PPG) based device for monitoring the heart rate of the subject and generating the timestamped variable BPM input streams for: (1) training of said artificial RNN model; and (2) feeding to the trained said artificial RNN model, to generate respective variable blood glucose level (BGL) output streams predictions based thereof.
Frank teaches a “photoplethysmography device that measures a signal indicative of a photoplethysmogram signal” (abstract), times of peaks (pg. 2, paragraph [7]), which is used to train the model (pg. 9, paragraph [103]), and using the machine learning trained model to generate measurements (pg. 20, paragraph [196]).
Claim 4 recites said RNN model's blood glucose level (BGL) predictions output streams are postprocessed to detect a specific value or values-trends indicative of a glucose event; and, wherein detection of a glucose event triggers the relaying of a notification including one or more of said RNN model's blood glucose level (BGL) predictions associated with the detected event.
Bidet teaches predicting glycemia (pg. 5, paragraph [129]), where a glucose event is interpreted as reading on glycemia, and displaying a recommendation to the patient (pg. 5, paragraph [130]), and a minimum glycemia level below which not to fall (pg. 5, paragraph [135]), where a specific value is interpreted as this minimum glycemia level.
Claim 7 recites said CGM device is a noninvasive wearable CGM device.
Frank teaches a glucose monitoring device which is noninvasive (pg. 2, paragraph [7]) and which can be worn (pg. 2, paragraphs [8-9]).
Claim 8 recites the monitored subject's BPM inputs to said RNN model are preprocessed to take the form of a scalar representing the heart rate value of the subject at a specific timepoint.
Frank teaches determining the heart rate of the user via the photoplethysmogram device (pg. 17, col. 1, paragraph [166]), where a heartrate may be a single value and thus a scalar.
Claim 9 recites the monitored subject's BPM inputs to said RNN model are preprocessed to take the form of a vector representing several consecutive heart rate values of the subject.
Frank teaches input of consecutive BPM readings based on the photoplethysmogram (Fig. 1d), where multiple consecutive readings are interpreted as vector.
Claim 10 recites a first network section of said RNN consists of a memory-based architecture, for connecting between BPM input series and BGL output series.
Frank teaches an RNN with long short-term memory architecture (pg. 15, paragraph [155]), which is interpreted as a memory-based architecture.
Claim 16 recites said memory-based section of said RNN outputs a single prediction over multiple input data timestamps.
Bidet teaches predicting at least one glycemia event using the RNN (pg. 3, paragraph [71]), which includes a single prediction.
Claim 17 recites wherein said memory-based section of said RNN outputs multiple predictions, corresponding to multiple input data timestamps.
Bidet teaches predicting at least one glycemia event using the RNN (pg. 3, paragraph [71]), which includes a multiple predictions.
Combining Frank and Bidet
An invention would have been obvious to one of ordinary skill in the art if some motivation in the prior art would have led that person to modify prior art reference teachings to arrive at the claimed invention prior to the effective filing date of the invention. One would have been motivated to combine the work of Bidet, which teaches predicting a glycemic (blood glucose) event using an RNN incorporating a loss function, with the teaching of Frank because Bidet teaches such a function minimizes the error as part of optimization of the neural network (pg. 10, col. 2, paragraphs [352-354]). Reducing the error in the model is a desirable characteristic in predicting blood glucose level using a neural network, which both Frank and Bidet are directed to. Because Bidet’s neural network successfully uses a loss function, it is expected that Frank’s neural network would as well. Therefore, the invention is prima facie obvious.
Claims 5-6
Claims 5-6 are rejected under 35 U.S.C. 103 as being unpatentable over Frank in view of Bidet as applied to claims 2-4, 7-10, 16-17, and 20 above and further in view of Stivoric (US 2009/0177068 A1; newly cited).
Claim 5 recites an accelerometer concurrently monitoring the subject, wherein said accelerometer output values are utilized for mitigating false-positive alerts detected within said RNN model's BGL level outputs.
Frank teaches an accelerometer (pg. 4, paragraph [58]) but not for mitigating false positive alerts.
Stivoric teaches incorporation of accelerometer into a blood glucose monitoring system and may thus be used to filter or subtract out from the signal detected by the heart rate sensor caused by body movement (paragraph [182]).
Claim 6 recites said accelerometer output values are analyzed to detect 'higher than normal' values occurring concurrently with glucose events detected within said RNN model's BGL values outputs; and, wherein at least part of said RNN model's detected glucose events - time overlapping with 'higher than normal' accelerometer values - are not regarded as glucose events, due to their overlapping time occurrence with higher physical activity indications that are based on said accelerometer output values.
Stivoric teaches a system using multiple signals to measure a state parameter, such as blood glucose level. Stivoric teaches a concurrent accelerometer and heart beat sensor, where the accelerometer can screen for movement, such as footfalls, which would product artifacts in the heart beat sensor data which are not indicative of elevated heart rate (paragraph [182]).
Combining Frank, Bidet, and Stivoric
An invention would have been obvious to one of ordinary skill in the art if some motivation in the prior art would have led that person to modify prior art reference teachings to arrive at the claimed invention prior to the effective filing date of the invention. One would have been motivated to combine the work of Stivoric, which teaches incorporating an accelerometer in blood glucose detection, with the teachings of Frank and Bidet because Stivoric teaches an accelerometer can be used to filter out non-heart parameter- related data as motion artifacts (pg. 22, col. 2, paragraph [182]). Frank teaches the value of multiple sensors to address noisy measurements due to movement (pg. 36, col. 2, paragraph [348]), and so it would be obvious to use a sensor in addition to the heartbeat sensor, such as an accelerometer taught by Stivoric, to reduce similar artifacts. Frank, Bidet, and Stivoric are all directed to blood glucose level prediction which may use a neural network, and thus their combination would be expected to succeed. Therefore, the invention is prima facie obvious.
Claims 11 and 14-15
Claims 11 and 14-15 are rejected under 35 U.S.C. 103 as being unpatentable over Frank in view of Bidet as applied to claims 2-4, 7-10, 16-17, and 20 above and further in view of Dalal (US 2020/0176121 Al; newly cited).
Claim 11 recites a second network section of said RNN consists of one or more fully-connected layers, for yielding a final output of the model in the form of a predicted BGL value of the monitored subject at a specific timepoint - based on the output of said memory-based section.
Dalal teaches monitoring and predicting blood glucose levels using recurrent neural networks that are fully connected (paragraph [108]).
Claim 14 recites the variable heart beats per minute (BPM) input streams of the monitored subject are pre-processed prior to being fed to said RNN by application of a learnable embeddings function.
Dalal teaches embedding the sensor data (paragraph [19]).
Claim 15 recites non-convolutional layers; Frank teaches a model which may include a convolution neural network (pg. 31, paragraph [308]), where the optionality of ‘may’ implies non-convolutional layers.
Combining Frank, Bidet, and Dalal
An invention would have been obvious to one of ordinary skill in the art if some motivation in the prior art would have led that person to modify prior art reference teachings to arrive at the claimed invention prior to the effective filing date of the invention. One would have been motivated to combine the work of Dalal, which teaches detailed aspects of the neural network used for biophysical modeling and prediction, with the teachings of Frank and Bidet because Dalal teaches, for instance, embedding for translating real numbers into machine learning readable vectors (pg. 22, col. 2, paragraph [232]). Frank teaches a convolution neural network which is optional (pg. 36, paragraph [347]), thus suggesting interchangeability between the convolutional and non-convolutional neural network embodiments. Frank, Bidet, and Dalal are all directed to blood glucose level prediction which may use a neural network, and thus their combination would be expected to succeed. Therefore, the invention is prima facie obvious.
Claims 12-13
Claims 12-13 are rejected under 35 U.S.C. 103 as being unpatentable over Frank in view of Bidet and Dalal as applied to claims 2-4, 7-11, 14-17, and 20 above and further in view of Quinn (Experimental Design and Data Analysis for Biologists, Cambridge University Press, 552 pgs., 2002; newly cited).
Claim 12 recites the variable heart beats per minute (BPM) input streams of the monitored subject are pre-processed prior to being fed to said RNN by application of a logarithmic function on the raw input values.
Quinn teaches biological data is commonly log transformed (pg. 64, col. 2, third paragraph).
Claim 13 recites said first network section of said RNN includes convolutional layers.
Frank teaches a model which may include a convolution neural network (pg. 31, paragraph [308]).
Combining Frank, Bidet, Dalal, and Quinn
An invention would have been obvious to one of ordinary skill in the art if some motivation in the prior art would have led that person to modify prior art reference teachings to arrive at the claimed invention prior to the effective filing date of the invention. One would have been motivated to combine the work of Quinn, which teaches biological experiment design, with the teachings of Frank, Bidet, and Dalal because Quinn teaches log transforming the data is the default for biological data because it is monotonic, transforms data to closer to normal, and reduces outlier influence (pg. 64, col. 2, third paragraph and following bullets). Frank, Bidet, and Dalal are all directed to analysis of biological data, including blood glucose level and heart rate, and thus their combination would be expected to succeed given the commonness of transforming biological data. Therefore, the invention is prima facie obvious.
Claims Free of the Prior Art
Claim 18, which recites said RNN model's BGL values outputs are analyzed for the detection of glucose events, based on a classification scheme, selected from the group including: (1) detection of an anomaly, based on one or more peaks in said RNN model's BGL values outputs - wherein a peak is defined as an increase beyond a threshold size of the BGL values outputs, the increase occurring within a time period shorter than a threshold length time period; (2) classifying the anomaly as either a food intake related or physical activity related anomaly; and (3) reacting only to anomalies classified as food intake related, is considered free of the prior art. Similar art, such as Bidet and Dalal, teach change in the heart rate monitoring sensor data based on food (Bidet: pg. 3, paragraph [66]) and physical activity (Bidet: pg. 3, paragraph [69]) and the machine learning algorithm can be used to detect anomalous data (Dalal: paragraph [112]), do not teach the requirement of classification of exercise versus food and exclusively alerting the presence of an anomaly as a result of food.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Robert J Kallal whose telephone number is (571)272-6252. The examiner can normally be reached Monday through Friday 8 AM - 4 PM 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, Olivia M. Wise can be reached at (571) 272-2249. 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.
/R.J.K./Examiner, Art Unit 1685
/OLIVIA M. WISE/Supervisory Patent Examiner, Art Unit 1685