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 .
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 3/21/2023 was received and placed in the record on file. The submission is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Priority
Receipt is acknowledged of certified copies of papers required by 37 CFR 1.55.
Election/Restrictions
Applicant’s election without traverse of group II, claims 8-15 in the reply filed on 9/29/2025 is acknowledged.
Claims 1-7 are withdrawn from further consideration pursuant to 37 CFR 1.142(b) as being drawn to a nonelected group I, there being no allowable generic or linking claim. Election was made without traverse in the reply filed on 9/29/2025.
Claim Objections
Claim 15 is objected to because of the following informalities: It appears that the “4” in line 2 should be deleted from the claim in view of the amendment to make claim 15 dependent on claim 8. Appropriate correction is required.
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 8-15 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Regarding claim 8; Independent claim 8 is a process (Step 1: Yes) and is directed to a judicial exception regarding abstract idea and mathematical concepts (Step 2A, Prong 1: Yes). The abstract idea is bolded in the recreated claim below:
A photoplethysmography-based non-invasive diabetes prediction method, comprising the following steps:
1) obtaining a pulse wave signal of human body;
2) eliminating low-frequency respiratory disturbances from the pulse wave signal;
3) obtaining multifractal spectrum features of the pulse wave signal on the basis of wavelet transform;
4) performing dimensionality reduction and clustering of feature space of the pulse wave signal;
5) establishing a screening model; and
6) performing prediction of new samples according to the screening model.
The claim encompasses an abstract idea drawn to a mental process that can be done in the human mind and mathematical concepts. In this case steps 2, 3 and 4 refer to mathematical concepts of using mathematical calculations such as filtering (eliminating low-frequency disturbances from the data); mathematical transforms (obtaining multifractal spectrum features of the pulse wave signal using a wavelet transform); and dimensionality reduction (transforming data set to a low dimensional space). Steps 4 and 5 are drawn to the mental processes of identifying classifications (clustering of feature space of the dimensionally reduced data); determining classifications (mental process of determining where the where/how to distinguish between classifications); and applying the screening model (mentally determining where new samples should be classified based on the previous mental process of distinguishing classifications). Said another way the mental process includes an observation, evaluation, judgment and opinion.
Further, the claim does not recite any additional elements that integrate the judicial exception into a practical application (Step 2A, Prong 2: No). The claim fails to recite an additional element or a combination of additional elements to apply, rely on, or use the judicial exception in a manner that imposes a meaningful limitation on the judicial exception. The additional step of obtaining a pulse wave signal and/or the performing a prediction of new samples according to the screening model does not improve a improvement to the technological field, the steps do not effect a particular treatment or effect a particular change based on the evaluated quality, nor does the method use a particular machine to perform the abstract idea.
Finally, the claim as a whole does not include additional elements that a sufficient to amount to significantly more than the judicial exception (Step 2B: No). The additional elements of “obtaining a pulse wave signal of human body” and/or “performing prediction of new samples according to the screening model” are mere extra-solution activity of “obtaining data” and “using the screening model” which are not tied to any tangible elements and are understood as activity incident to the primary process. “Obtaining the pulse wave signa of human body” is a mere pre-solution activity of gathering data for use in the claimed process; and “performing prediction of new samples according to the screening model” is mere post solution activity of putting the screening model into use to output a result. See MPEP 2106.05(g).
Accordingly, claim 8 is rejected as non-statutory as being directed to a judicial exception (abstract idea) without significantly more.
Dependent claims 9-15 recite further mathematical steps that further define the abstract idea/mathematical concepts that were already recited in independent claim 8 and do not reduce the abstract idea to a practical application to amount to significantly more than the abstract idea when considered on the whole. Rather, the recitation of further abstract ideas (the further steps that define the wavelet transform and how its implemented [step 3], claims 9-11; steps for how the dimensionality is reduced and the type of clustering is performed [step 4], claims 12-13; further details of the screening model [step 5], claim 14; and further defining steps of performing the prediction using the model [step 6], claim 15) within another abstract idea (steps 3-6) does not render the claim non-abstract (see MPEP 2106 II. A. 2.).
As such, claim 9-15 are rejected as non-statutory as being directed to a judicial exception (abstract idea) without significantly more.
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 8 and 12-14 are rejected under 35 U.S.C. 103 as being unpatentable over Zhang et al (CN 107296616 A, citation relies on examiner provided machine translation) in view of Jayaraman (US 2017/0143279 A1), Shtar et al (examiner provided NPL “Clustering and Dimensionality Reduction: Understanding the ‘Magic’ Behind Machine Learning”) and Practicus AI (examiner provided NPL “The 5 Clustering Algorithms Data Scientists Need to Know”).
Regarding claims 8 and 12-14; Zhang discloses a photoplethysmography-based non-invasive glucose level prediction method (abstract), comprising the following steps:
obtaining a pulse wave signal of human body (step S31-S32; page 7, paragraph 2-4; figure 3);
eliminating low-frequency respiratory disturbances from the pulse wave signal (wherein respiratory disturbances are noise and DC components of the obtained signal which are filtered out in the pre-processing step; page 4, paragraph 4; page 6, paragraph 2; page 9, paragraph 1);
obtaining multifractal spectrum features of the pulse wave signal on the basis of wavelet transform (feature extraction module utilizes wavelet transform to obtain multifractal spectrum features of the pulse wave signal; step S33 of figure 3 and steps S331-S333 of figure 5; page 7, paragraph 5 and page 8, 5 through page 9, paragraph 3).
establishing a screening model (wherein a prediction neural network is setup and trained; step S34 of figure 3; page 7, paragraph 6 through page 8, paragraph 1); and
performing prediction of new samples according to the screening model (using the established prediction neural network to detect blood glucose predictions; step S35 of figure 3; page 8, paragraphs 2-5).
While Zhang discloses using the non-invasive method and predictive model for predicting a blood glucose, it does not explicitly disclose a diabetes prediction method.
Jararaman teaches a similar non-invasive method using a PPG signal for determining if a patient is normal, pre-diabetic or diabetic based on a glucose level and a machine learning tool (paragraph [0004], [0032]-[0034]; figure 3).
Therefore, it would have been obvious to one of ordinary skill in the art at the time of filing to modify Zhang’s method for predicting diabetes based on the predicted glucose as taught by Jayaraman.
Further regarding claims 8 and 12-14; while Zhang does disclose use of a predictive neural network; it does not explicitly disclose the details of performing dimensionality reduction and clustering of feature space of the pulse wave signal.
Shtar teaches the details of machine learning and the processes/steps that go into developing the predictive machine learning models including dimensionality reduction which is used to reduce the number of features under consideration (“Dimensionality Reduction” section of Shtar) and clustering of feature space which is used to identify classifications to make sure objects in different groups are not similar and object is the same group are similar in order to define the hidden structure of the data (“Clustering” section of Schtar) allowing for predictive modeling using machine learning (Summary section of Shtar). Practicus AI further teaches known algorithms for clustering as a machine learning tool for grouping data points used to classify each data point into a specific group (Introduction of Practicus AI).
Regarding claims 8 and 12-14; Zhang discloses the use of predictive machine learning on PPG data in order to determine blood glucose. Shtar and Practicus AI teach the details of how collected data is used to develop and input into a machine learning model using dimensionality reduction and clustering to determine the classification groups of the features extracted from the data. Therefore, it would have been obvious to one of ordinary skill in the art at the time of filing to further modify the Zhang/Jayaraman method to perform dimensionality reduction and clustering of feature space of the collected data as taught by Shtar and Practicus AI in order to build/train Zhang/Jayarama’s predictive machine learning model/neural network for predicting diabetes in a patient.
Further regarding claim 12-13; the Zhang/Jayarama/Shtar/Practicus AI combination is described above and teaches using collected data to generate a machine learning predictive model. Furthermore, Shtar and Practicus AI teaches the details include methods of creating the machine learning predictive model comprises generating a photoplethysmography information database, extracting features and performing normalization on the features, and performing principal component analysis on the feature space to realize feature dimensionality reduction (claim 12, taught in Shtar) and the clustering the feature space after dimensionality by K-means or KNN unsupervised learning, setting a number of clusters, logging the distance of each data item to the center of each cluster, and classifying the data according to the number of clusters (claim 13, taught in Shtar and Practicus AI).
Further regarding claim 14; the Zhang/Jayarama/Shtar/Practicus AI combination is described above and teaches using collected data to establish binary classification prediction models for the clustering results respectively (wherein Zhang teaches either placing the new measurement in the classification or not; Jayarama teaches classifying into one of the identified classifications; and Shtar/Practicus AI teach the classification models for determined clusters).
Claims 9-11 are rejected under 35 U.S.C. 103 as being unpatentable over Zhang in view of Jayarama, Shtar and Practicus AI as applied to claim 8 above, and further in view of Joshi et al (examiner provided NPL “Arterial Pulse System: Moder Methods for Traditional Indian Medicine”).
The Zhang/Jayarama/Shtar/Practicus AI combination is described in the rejection of claim 8 above, however it does not explicitly disclose the details of the wavelet transform for obtaining multifractal spectrum features of a pulse wave.
Joshi teaches the use of wavelet transform modulus maxima to obtain multifractal spectrums in a pulse waveform which can be used as important features in the classification process to identify other physiological information from a pulse waveform by feeding the wavelet transform data into machine learning algorithms to identify diseases from the pulse waves.
Regarding claims 9-11; Zhang discloses using a wavelet transform modulus maxima (WTMM) Method (wherein Zhang discloses the embodiment uses wavelet transform modulus maximal sequence; page 9, paragraphs 2 and 3). Therefore, Zhang/Jayarama/Shtar/Practicus AI combination teaches uses predictive machine learning model to classify information obtained from a WTMM transform. Joshi teaches the known steps of calculating and obtaining multifractal spectrum coordinates and cumulative coefficients using a WTMM method (claim 9) and other steps used during WTMM to obtain features from the pulse wave including the steps as recited in claims 10 and 11 for the purpose of feeding data the data into a predictive machine learning model to diagnose diseases. Therefore, it would have been obvious to one of ordinary skill in the art at the time of filing to modify the Zhang/Jayarama/Shtar/Practicus AI combination to utilize Joshi’s method of obtaining multifractal spectrum features from a pulse wave in order to assist/improve in classifying the collected pulse wave data to create a predictive machine learning model for identifying a patient as either, normal, pre-diabetic or diabetic.
Claim 15 is rejected under 35 U.S.C. 103 as being unpatentable over Zhang in view of Jayarama, Shtar and Practicus AI combination as applied to claim 8 above, and further in view of Brownlee (examiner provided NPL “A Gentle Introduction to Probability Scoring Methods in Python”).
The Zhang/Jayarama/Shtar/Practicus AI combination is described in the rejection of claim 8 above; however, it does not explicitly disclose the performing prediction of new samples step further comprises weighting distances of the features of new samples to the centers of the clusters, and predicting a probability according to the weighting result.
Brownlee teaches known methods in predictive machine learning models of utilizing predicted probabilities and scoring rules for predicting the probability/evaluating the accuracy of a prediction of the model, including based on the distance of the data point to the center of a cluster (see Log Loss and Brier Scores).
Regarding claim 15; the Zhang/Jayarama/Shtar/Practicus AI combination teaches using a predictive machine learning model to predict a patient as normal, pre-diabetic or diabetic. Brownlee teaches it is known in machine learning models to determine a predicted probability based on weighted distance to a cluster center. Therefore, it would have been obvious to one of ordinary skill in the art at the time of filing to further modify the Zhang/Jayarama/Shtar/Practicus AI combination to further weight distances of features of new samples to the centers of clusters as taught by Brownlee in order to provide the predicted probability that the learning model prediction is correct/accurate, thus providing a level of confidence to the prediction.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
US 2020/0323493 A1 to Arora et al; discloses a system for analyzing PPG signals.
US 2020/0352517 A1 to Jos et al; discloses a method of preprocessing NIR Spectroscopy data for non-invasive glucose monitoring and apparatus thereof.
US 10,420,470 B2 to Kwon et al; discloses an apparatus and method for detecting biological information.
US 10,888,280 B2 to Newberry; discloses a system and method for obtaining health data using a neural network.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ADAM J EISEMAN whose telephone number is (571)270-3818. The examiner can normally be reached Monday - Friday (7:00 AM - 4:00 PM).
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, Jacqueline Cheng can be reached at 571-272-5596. 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.
/ADAM J EISEMAN/ Primary Examiner, Art Unit 3791