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 .
The present Office Action is in response to the Request for Continued Examination dated 22 September 2025.
Request for Continued Examination
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 22 September 2025 has been entered.
DETAILED ACTION
In the amendment filed 22 September 2025:
Claim 11 is cancelled
Claims 18-21 are new
Claims 1-2,6-7,10,12,14-17 are amended
Claims 1-2,4-10,12-21 are pending
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 1-21 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more.
Claims 1, 16-17 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. The claim recites methods and a system, which are within a statutory category. The limitations of:
Claim(s) 1,16-17 (Claim 17 being representative)
prompt an individual to perform a predetermined sequence of activities, the predetermined sequence of activities including at least one exertion, the at least one exertion including a predetermined action configured to induce a physiological or mechanical change in the individual that is predictive of a presence of the disorder;
in operable communication with and worn on a body of the individual, for generating physiological screening data for screening the individual for a disorder;
access the physiological screening data, wherein the physiological screening data includes raw sensor information;
process the raw sensor information to derive a plurality of physiological signals from each activity of the predetermined sequence of activities, the plurality of physiological signals from each activity collectively predictive for detecting the presence of the disorder;
quantify properties of each physiological signal of the plurality of physiological signals from each activity of the predetermined sequence of activities by extracting a plurality of features from the plurality of physiological signals, the plurality of features including spectral and statistical features;
and compute an output defining a probability measure of risk of a positive diagnosis of the disorder attributable to the individual by applying the plurality of features extracted from the physiological screening data to receive and perform multi-modal analysis of the plurality of features, parameters being configured, based on the plurality of features, to maximize a probability of detecting the disorder.
as drafted, is a process that, under the broadest reasonable interpretation, covers certain methods of organizing human activity (i.e., managing personal behavior including following rules or instructions) but for recitation of generic computer components. That is, other than reciting a non-invasive system, sensor system, processor and computing device, the claimed invention amounts to managing personal behavior or interaction between people. For example, but for the non-invasive system, sensor system, processor and computing device, this claim encompasses screening patients for a disorder in the manner described in the identified abstract idea, supra. If a claim limitation, under its broadest reasonable interpretation, covers managing personal behavior or interactions between people but for the recitation of generic computer components, then it falls within the “certain methods of organizing human activity” grouping of abstract ideas. Accordingly, the claim recites an abstract idea.
This judicial exception is not integrated into a practical application. In particular, the claims recite the additional elements of a non-invasive system, sensor system, processor and computing device that implements the identified abstract idea. The non-invasive system, sensor system, processor and computing device are not described by the applicant and is recited at a high-level of generality (i.e., a generic server performing generic computer functions) such that it amounts no more than mere instructions to apply the exception using a generic computer component. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claim is directed to an abstract idea.
The claim further recites the additional element of using a trained machine learning model to screen patients for a disorder. This represents mere instructions to implement the abstract idea on a generic computer. Implementing an abstract idea using a generic computer or components thereof does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. See, e.g., Recentive Analytics, Inc. v. Fox Corp., No. 2023-2437 at 10 (Fed. Cir. April 18, 2025) (finding that claims that do no more than apply established methods of machine learning to a new data environment are ineligible). Alternatively, or in addition, the implementation of the trained machine learning model to screen patients for a disorder merely confines the use of the abstract idea (i.e., the trained model) to a particular technological environment or field of use (logistic regression, support vector machines, decision trees, ensemble methods, or neural networks (deep learning)) and thus fails to add an inventive concept to the claims.
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional elements of using a non-invasive system, sensor system, processor and computing device to perform the noted steps amounts to no more than mere instructions to apply the exception using a generic computer component. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept (“significantly more”).
As discussed above with respect to integration of the abstract idea into a practical application, the additional element of using the trained machine learning model to screen patients for a disorder was found to represent mere instructions to implement the abstract idea on a generic computer and/or confine the use of the abstract idea (i.e., the trained model) to a particular technological environment or field of use (logistic regression, support vector machines, decision trees, ensemble methods, or neural networks (deep learning)). This has been re-evaluated under the “significantly more” analysis and determined to be insufficient to provide significantly more. MPEP 2106.05(I) indicates that mere instructions to implement the abstract idea on a generic computer and/or confining the use of the abstract idea to a particular technological environment or field of use cannot provide significantly more. See also Recentive Analytics, Inc. v. Fox Corp., No. 2023-2437 at 17 (Fed. Cir. April 18, 2025) (finding that applying machine learning to an abstract idea does not transform a claim into something significantly more).
Claims 2,4-10,12-15,18-21 are similarly rejected because they either further define/narrow the abstract idea and/or do not further limit the claim to a practical application or provide as inventive concept such that the claims are subject matter eligible even when considered individually or as an ordered combination.
Claim(s) 2 merely describe(s) configuring the machine learning model, which further defines the abstract idea. The claim further recites “training a machine learning model.” When given its broadest reasonable interpretation in light of the disclosure, the training of a machine learning model to screen patients for a disorder represents the creation of mathematical interrelationships between data. As such, the training of the machine learning model represents a mathematical concept that is interpreted to be part of the identified abstract idea, supra. The types of identified abstract ideas are considered together as a single abstract idea for analysis purposes
Claim(s) 4 merely describe(s) aggregation of data, which further defines the abstract idea.
Claim(s) 5-6 merely describe(s) the plurality of features used, which further defines the abstract idea.
Claim(s) 7 merely describe(s) how the physiological signals during a physiological screening are detected, which further defines the abstract idea.
Claim(s) 8 merely describe(s) the machine learning model as a probabilistic model, which further defines the abstract idea.
Claim(s) 9 merely describe(s) data used in the machine learning model, which further defines the abstract idea.
Claim(s) 10 merely describe(s) the type of physiological signals, which further defines the abstract idea.
Claim(s) 12-14 merely describe(s) the sensors used in the sensor system, which further defines the abstract idea.
Claim(s) 15 merely describe(s) the disorders detected and how its detected, which further defines the abstract idea.
Claim(s) 18 merely describe(s) selecting activities, which further defines the abstract idea.
Claim(s) 19 merely describe(s) recommending a treatment plan, which further defines the abstract idea.
Claim(s) 20 merely describe(s) administering a treatment, which further defines the abstract idea.
Claim(s) 21 merely describe(s) assessing treatment efficacy, which further defines the abstract idea.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The Examiner notes that the rejection will reference the translated documents (attached) corresponding to any foreign documents recited in the rejection.
Claims 1,16-21 is/are rejected under 35 U.S.C. 103(a) as being unpatentable over Heldman et al (US Publication No. 20140074179) in view of Howard et al (US Publication No. 20170251985).
Regarding Claim 1
Heldman teaches A non-invasive method of predicting a disorder diagnosis comprising:
generating physiological screening data by a sensor system worn on a body of an individual of a plurality of individuals for screening the individual for a disorder while the individual performs a predetermined sequence of activities, wherein the predetermined sequence of activities includes at least one exertion configured to induce a physiological or mechanical change in the individual that is predictive of a presence of the disorder [Heldman at Para. 0013 teaches the current standard in evaluating the severity of movement disorder symptoms in Parkinson's disease is the manually human scored Unified Parkinson's Disease Rating Scale (UPDRS) used to score motor tests, many of which involve repetitive movement tasks such as touching the nose and drawing the hand away repeatedly, or rapidly tapping the fingers together. A battery of exercises, typically a subset of the upper extremity motor section of the UPDRS, is normally completed during DBS lead placement surgery and subsequent programming sessions to evaluate performance while a clinician qualitatively assesses symptoms. Each test is evaluated by a clinician based solely on visual observation and graded on a scale that ranges from 0 (minor) to 4 (severe); Heldman at Para. 0023 teaches movement may be continuously measured over long time spans, or may be measured only over a short time span, for example, as during the period of one or more tests taken from or based on the UPDRS motor exam. A measurement time period comprises two separate time periods: (i) a sensing time during which the movement disorder diagnostic device and its included sensors are used to sense and measure the subject's external physical motion; and (ii) a processing or calculation time wherein the measured motion data is used to calculate objective scores and/or other kinematic data that quantify the severity of the subject's movement disorder symptoms and side effects, and wherein the scores];
accessing by a processor of a plurality of processing elements the physiological screening data [Heldman at Para. 0026 teaches following measurement of symptomatic movement, the next step in objective quantification of a subject's movement disorder symptoms is the extraction of statistical kinematic features from the acquired movement data via processing. This processing may take place during or following data acquisition and may occur within a movement data acquisition device or within a different processing device, such as a personal computer, PDA, smart phone, tablet computer, touch screen interface, or the like, with which the acquisition device interfaces, either through a cable connection or by wireless transmission];
conducting signal processing, by the processor from raw sensor information of the physiological screening data to derive a plurality of physiological signals from each activity of the predetermined sequence of activities, the plurality of physiological signals collectively predictive for detecting the presence of the disorder [Heldman at Para. 0114 teaches the command module 3 may perform rudimentary signal processing, such as filtering and analog-to-digital conversion, on the movement signals received from the sensor unit 2 before transmitting the movement signals to a receiver unit 5.];
quantifying, by the processor, properties of each physiological signal of the plurality of physiological signals from each activity of the predetermined sequence of activities by extracting a plurality of features from the plurality of physiological signals, the plurality of features including … [ … ] … and statistical features [Heldman at Para. 0026];
wherein the presence of a clinician is not required while the individual performs the predetermined sequence of activities [Heldman at Para. 0030 teaches additionally, the present invention increases access to geographically disparate populations by putting the expertise into the system and reducing or eliminating the need for an expert or trained clinician to be present with each subject].
Heldman does not teach [ … ] … spectral … [ … ]
and computing, by the processor, an output defining a probability measure of risk of a positive diagnosis of the disorder attributable to the individual by applying the plurality of features extracted from the physiological screening data to a single machine learning model operable to receive and perform multi-modal analysis of the plurality of features, wherein parameters of the machine learning model being configured, based on the plurality of features, to maximize a probability of detecting the disorder,
Howard teaches [ … ] … spectral [Howard at Para. 0380 teaches spectral centroid is the center of gravity of the magnitude spectrum of the STFT. Here, Mi [n] denotes the magnitude of the Fourier transform at frequency bin n and frame i. The centroid is used to measure the spectral shape; Howard at Para. 0381 teaches spectral rolloff is the feature defined by the frequency Rt such that 85% of the frequency is below this point] … [ … ]
and computing, by the processor, an output defining a probability measure of risk of a positive diagnosis of the disorder attributable to the individual by applying the plurality of features extracted from the physiological screening data to a single machine learning model operable to receive and perform multi-modal analysis of the plurality of features, wherein parameters of the machine learning model being configured, based on the plurality of features, to maximize a probability of detecting the disorder [Howard at Para. 0008 teaches in an embodiment, the physical and chemical phenomena may comprise at least one of electroencephalographic monitoring, linguistic assessment, behavioral tracking, facial feature analysis, mood state, cognitive state, language analysis, speech, and vocal impairments, modes of speaking, and body movement. The pattern analysis may comprise at least one of language analysis using machine learning, syntactic structure identification, multilayered perceptron neural networks, machine translation processes, case-based reasoning, analogy-based reasoning, speech-based cognitive assessment, mind default axiology, mood state indicator, linguistic-axiological input/output, and mind default axiology Howard at Para. 0412 teaches a follow up study with larger datasets, varied subject groups, and additional extraction features will be conducted. Additional studies using combinations of multi-modal data of movement, language, and facial features will also be conducted],
It would have been prima facie obvious skill in the art, at the time of effective filing, to combine sensors of Heldman with the machine learning model of Howard with the motivation to improve detection of detection of disease conditions and comorbidities [Howard at Para. 0005].
Regarding Claim 16
Heldman teaches a non-invasive method of predicting a disorder diagnosis, comprising:
prompting an individual of a plurality of individuals to perform a predetermined sequence of activities, the predetermined sequence of activities including at least one exertion configured to induce a physiological or mechanical change in the individual that is predictive of a presence of a disorder [Heldman at Para. 0045 teaches a method of tuning a movement disorder therapy system comprising steps of providing a movement disorder diagnostic device to a subject having a deep brain stimulation (DBS) device with a first level of DBS parameters, the movement disorder diagnostic device comprising at least one physiological or movement sensor having a signal, and a processor comprising an algorithm, displaying on a programming device a list of activities, actions or tasks for the subject to select from, having the subject elect at least one activity, action or task from the list on the programming device, selecting with the movement disorder diagnostic device a predetermined set of DBS parameters corresponding to the elected at least one activity, action or task, and entering with the programming device the group of selected DBS parameters corresponding to the at least one elected activity, action or task into the subject's DBS device such that the subject's DBS device operates under the selected group of DBS parameters while the subject performs the at least one elected activity, action, or task];
generating, by a sensor system worn on a body of the individual, physiological screening data from each activity of the predetermined sequence of activities for screening the individual for the disorder [Heldman at Para. 0013, 0023 (see Claim 1 for explanation)];
accessing, by a processor of a plurality of processing elements, the physioloqical screening data [Heldman at Para. 0013, 0023 (see Claim 1 for explanation)];
processing, by the processor, raw sensor information of the physioloqical screening data to derive a plurality of physioloqical signals from each activity of the predetermined sequence of activities, the plurality of physiological signals from each activity collectively predictive for detecting the presence of the disorder [Heldman at Para. 0114 (see Claim 1 for explanation)];
quantifying, by the processor, properties of each physiological signal of the plurality of physiological signals from each activity of the predetermined sequence of activities by extracting a plurality of features from the plurality of physiological signals, the plurality of features including … [ … ] … and statistical features [Heldman at Para. 0026 (see Claim 1 for explanation)];
Heldman does not teach [ … ] … spectral … [ … ]
and computing, by the processor, an output defining a probability measure of risk of a positive diagnosis of the disorder attributable to the individual by applying the plurality of features extracted from the physiological screening data to a single machine learning model operable to receive an perform multi-modal analysis of the plurality of features, the machine learning model including parameters that are configured, based on the plurality of features, to maximize a probability of detecting the disorder.
Howard teaches [ … ] … spectral [Howard at Para. 0380-0381 (see Claim 1 for explanation)] … [ … ]
and computing, by the processor, an output defining a probability measure of risk of a positive diagnosis of the disorder attributable to the individual by applying the plurality of features extracted from the physiological screening data to a single machine learning model operable to receive an perform multi-modal analysis of the plurality of features, the machine learning model including parameters that are configured, based on the plurality of features, to maximize a probability of detecting the disorder [Howard at Para. 0008, 0412 (see Claim 1 for explanation)].
It would have been prima facie obvious skill in the art, at the time of effective filing, to combine sensors of Heldman with the machine learning model of Howard with the motivation to improve detection of detection of disease conditions and comorbidities [Howard at Para. 0005].
Regarding Claim 17
Heldman teaches A non-invasive system for predicting a disorder, comprising:
a computing device configured to prompt an individual to perform a predetermined sequence of activities, the predetermined sequence of activities including at least one exertion, the at least one exertion including a predetermined action configured to induce a physiological or mechanical change in the individual that is predictive of a presence of the disorder [Heldman at Para. 0045 (see Claim 16 for explanation)];
a sensor system in operable communication with the computing device and worn on a body of the individual, for generating physiological screening data for screening the individual for a disorder [Heldman at Para. 0013, 0023 (see Claim 1 for explanation)];
and a processor in operable communication with the sensor system, wherein the processor is configured to [Heldman at Para. 0076 teaches the sensor unit further preferably comprises a digital motion processor (DMP) which may perform some preprocessing or processing of the sensor signals using motion-related algorithms]:
access the physiological screening data, wherein the physiological screening data includes raw sensor information [Heldman at Para. 0013, 0023 (see Claim 1 for explanation)];
process the raw sensor information to derive a plurality of physiological signals from each activity of the predetermined sequence of activities, the plurality of physiological signals from each activity collectively predictive for detecting the presence of the disorder [Heldman at Para. 0114 (see Claim 1 for explanation)];
quantify properties of each physiological signal of the plurality of physiological signals from each activity of the predetermined sequence of activities by extracting a plurality of features from the plurality of physiological signals, the plurality of features including … [ … ] … and statistical features [Heldman at Para. 0026 (see Claim 1 for explanation)];
Heldman does not teach [ … ] … spectral … [ … ]
and compute an output defining a probability measure of risk of a positive diagnosis of the disorder attributable to the individual by applying the plurality of features extracted from the physiological screening data to a single machine learning model operable to receive and perform multi-modal analysis of the plurality of features, parameters of the machine learning model being configured, based on the plurality of features, to maximize a probability of detecting the disorder.
Howard teaches [ … ] … spectral [Howard at Para. 0380-0381 (see Claim 1 for explanation)]… [ … ]
and compute an output defining a probability measure of risk of a positive diagnosis of the disorder attributable to the individual by applying the plurality of features extracted from the physiological screening data to a single machine learning model operable to receive and perform multi-modal analysis of the plurality of features, parameters of the machine learning model being configured, based on the plurality of features, to maximize a probability of detecting the disorder [Howard at Para. 0008, 0412 (see Claim 1 for explanation)].
It would have been prima facie obvious skill in the art, at the time of effective filing, to combine sensors of Heldman with the machine learning model of Howard with the motivation to improve detection of detection of disease conditions and comorbidities [Howard at Para. 0005].
Regarding Claim 18
Heldman/Howard teach the method of claim 1,
Heldman/Howard further teach further comprising selecting a predetermined sequence of activities that are predictive of the presence of the disorder [Heldman at Para. 0122 teaches as noted above, however, in certain other embodiments, the display unit may not be programmed to alert a subject, but instead may simply be left available for a subject to input data regarding his or her symptoms or to select movement disorder assessment tasks to perform from among various options according to the subject's personal preferences and schedule as well as the subject's own subjective view of the severity of his or her symptoms].
Regarding Claim 19
Heldman/Howard teach the method of claim 1,
Heldman/Howard further teach further comprising recommending, by the clinician, a treatment plan based on the computed output, wherein the individual is a patient [Heldman at Para. 0031 teaches many embodiments of the present invention include optimization or tuning algorithm(s) which are used to determine or recommend optimum therapy settings or parameters.].
Regarding Claim 20
Heldman/Howard teach the method of claim 19,
Heldman/Howard further teach further comprising administering a treatment according to the recommended treatment plan to the patient [Heldman at Para. 0107 teaches the present invention further optionally allows the clinician, physician or technician the ability to review recommended second level therapy parameters before or after those therapy parameters or settings are entered into the therapy device and to change those recommended settings].
Regarding Claim 21
Heldman/Howard teach the method of claim 20,
Heldman/Howard further teach further comprising assessing, by the clinician, a treatment efficacy based on the computed output [Heldman at Para. 0127 teaches thus, by allowing monitoring over a longer period of time, a physician or other clinician or even researcher could use the movement disorder monitoring device of the present invention to collect objective data regarding a subject's disease progression and, hence, the efficacy of a given treatment at stopping or slowing a subject's disease progression.].
Claim 2 is rejected under 35 U.S.C. 103(a) as being unpatentable over Heldman, Howard as applied to claim 1 above, and further in view of JHA et al (Foreign Publication WO-2018128927-A1).
Regarding Claim 2
Heldman/Howard teach the method of claim 1,
Heldman/Howard further teach further comprising:
configuring the machine learning model, by:
accessing by at least one of the plurality of processing elements one or more training datasets, each of the one or more training datasets generated from an implementation of the sensor system worn on a body of a sample individual of the plurality of individuals as the sample individual performs the predetermined sequence of activities [Howard at Para. 0536 teaches the first generation of the project is referred to as the BCCS which will collect multiple data streams using noninvasive body sensors, and capture image and audio. It is intended for use at home and to be convenient and user friendly for the user. The second generation is the LEAPS device. It consists of the BCCS redefined to specifically target PTSD patients and contain a specific app that is an interactive tool to collect data. The LEAPS analysis uses the BCCS codes and algorithms to train classifiers. Unlike current evaluations that are being used, this app removes the need to face-to-face clinician involvement. Beyond the app, the LEAPS device will consist of upper limb sensors, lower limb sensors, EKG sensor, EEG electrodes, headphones, mic, and video recording. The games/tasks the patient is asked to complete will collect consistent data for each ToDM. The data collected will be related to specific biomarkers already established. The microphone and audio capture will collect language and speech data which will be reflected by the natural language processing analysis. Facial feature characterization will be classified using a face recognition software that measures a variety of values related to facial expression. This data will then be sent and stored in the cloud platform and stored anonymously];
Heldman/Howard do not teach and conducting signal processing by the processor for each of the one or more training datasets to derive a plurality of sample signals from one or more activities of the predetermined sequence of activities, wherein the machine learning model is trained and configured based on the plurality of sample signals.
JHA teaches and conducting signal processing by the processor for each of the one or more training datasets to derive a plurality of sample signals from one or more activities of the predetermined sequence of activities, wherein the machine learning model is trained and configured based on the plurality of sample signals [JHA at Para. 0068 teaches This tier uses WMS data to detect/track multiple diseases. As shown in Figure 3 the diagnostic decision flow of PHDS 14 is shown using six sequential stages: (1) selection of target physiological signals 32, (2) matching of these signals with their WMSs 34, (3) preprocessing of the collected signals for machine learning models (MLMs) pre-trained using machine learning systems 36, (4) decision making through MLMs 38, (5) obtaining disease signatures 40, and (6) responding according to the decisions 42. Diagnosis of disease i is done through its own tier-wise disease module 44. Using this structure, PHDS 14 can monitor any number n diseases in parallel; JHA at Para. 0087 teaches A decision maker 104, which stores the MLM, makes diagnostic predictions based on the latest domain knowledge extractable from an up-to-date training dataset on disease i, and thus acts as the core of a DDM].
It would have been prima facie obvious skill in the art, at the time of effective filing, to combine the references of Heldman, Howard with the signal processing of JHA with the motivation to improve the quality of clinical practice in healthcare.
Claims 4, 9 are rejected under 35 U.S.C. 103(a) as being unpatentable over Heldman, Howard, JHA as applied to claim 1 above, and further in view of Rao et al (US Publication No. 20190110754).
Regarding Claim 4
Heldman/Howard/JHA teach the method of claim 2,
Heldman/Howard/JHA do not teach further comprising:
aggregating by the processor the plurality of features across a portion of the plurality of sample signals for a portion of the predetermined sequence of activities, and applying all of the plurality of features as inputs to the machine learning model.
Rao teaches further comprising:
aggregating by the processor the plurality of features across a portion of the plurality of sample signals for a portion of the predetermined sequence of activities, and applying all of the plurality of features as inputs to the machine learning model [Rao at Para. 0074 teaches Thus, in certain embodiments, the purpose of the machine learning system is to take as input the temporal or static data recorded from the sensors and produce as output a probability score for each of a collection of diagnoses].
It would have been prima facie obvious skill in the art, at the time of effective filing, to combine the references of Heldman, Howard, JHA with the features of Rao with the motivation to improve symptoms associated with Parkinson's Disease or stroke [Rao at Para. 0029].
Regarding Claim 9
Heldman/Howard teach the method of claim 1,
Heldman/Howard do not teach further comprising:
applying to the machine learning model additional data derived from medical history information associated with the individual being screened or like individuals, diseases specific domain knowledge, or sensor features.
Rao teaches further comprising:
applying to the machine learning model additional data derived from medical history information associated with the individual being screened or like individuals, diseases specific domain knowledge, or sensor features [Rao at Para. 0078 teaches in certain embodiments, the machine learning system as a whole will take the data acquired during these tests and use them to produce the desired output. In other embodiments, the system may also integrate background information about a patient including but not limited to age, sex, prior medical history, family history, and results from any additional or alternate medical tests].
It would have been prima facie obvious skill in the art, at the time of effective filing, to combine the references of Heldman, Howard with the medical history information of Rao with the motivation to improve symptoms associated with Parkinson's Disease or stroke [Rao at Para. 0029].
Claim 5 is rejected under 35 U.S.C. 103(a) as being unpatentable over Heldman, Howard as applied to claim 1 above, and further in view of HAO et al (Foreign Publication CN-111407262-A) in view of Zia et al (US Publication No. 20140180153).
Regarding Claim 5
Heldman/Howard teach the method of claim 1,
Heldman/Howard do not teach wherein the plurality of features relate to averages, standard deviations, ranges, minimums, maximums, root- mean squared, quantiles, moments, entropy metrics, skewness, kurtosis, and linear and non-linear metrics.
HAO teaches averages, … [ … ] …, ranges, minimums, maximums, root-mean squared, quantiles, … [ … ] …, entropy metrics, skewness, kurtosis, and linear and non-linear metrics [HAO at Page 12 Para 12 teaches time domain characteristics: 10 common features for Heart Rate Variability (HRV) analysis were extracted, as well as 34 common statistical features on RR intervals, such as mean, quantile, range, etc. We also extracted 5 non-linear features including sample entropy, zero-crossing analysis. However, the abrupt changes in RR intervals are not well captured using these features alone. To solve this problem, we have devised three new features, as follows; HAO at Page 13 Para 12 teaches feature 5, RMSSD: root mean square of adjacent RR interval differences; HAO at Page 14 Para 19 teaches feature 35, rr _ range: RR interval maximum minus RR interval minimum; HAO at Page 15 Para 16 teaches similar to extracting features at RR intervals, we extracted 25 statistical features from the respiratory signal. For example, where the time domain features include mean and standard deviation of a sequence of respiratory peaks, kurtosis, skewness, etc., the frequency domain features include highest peak, energy values, etc].
It would have been prima facie obvious skill in the art, at the time of effective filing, to combine the references of Heldman, Howard with the metrics of Rao with the motivation to improve the classification of physiological signals.
Heldman/Howard /HAO do not teach [ … ] … standard deviations, …. [ … ] …., moments, … [ … ].
Zia teaches [ … ] … standard deviations, …. [ … ] …., moments, … [ … ] [Zia at Para. 0039 teaches the global detection algorithms 108 allow for the capturing and analysis of data set characteristics relating to inter-segment variability, segment non-Gaussianity, and general structure features of the edited signal. Variability parameters are based on the segment-to-segment variance of other feature parameters. Measures of non-Gaussianity include kurtosis and other higher-order moments, and are useful since signals associated with turbulence are generally non-Gaussian.].
It would have been prima facie obvious skill in the art, at the time of effective filing, to combine the references of Rao/HAO with the features of Zia with the motivation to improve detection of disease.
Claim 6 is rejected under 35 U.S.C. 103(a) as being unpatentable over Heldman, Howard as applied to claim 1 above, and further in view of Chiang et al ("Temporal and Spectral Characteristics of Dynamic Functional Connectivity between Resting-State Networks Reveal Information beyond Static Connectivity").
Regarding Claim 6
Heldman/Howard teach the method of claim 1,
Heldman/Howard do not teach wherein the plurality of features relate to frequency domain features including power spectral density features, peak frequency, power skewness, kurtosis, entropy, center, and spread.
Chiang teaches wherein the plurality of features relate to frequency domain features including power spectral density features, peak frequency, power skewness, kurtosis, entropy, center, and spread [Chiang teaches at Page 10 Para 2 teaches to capture the distributional properties of the power spectra, we examined the first four spectral central moments of dFC, including the (a) spectral centroid (SCO), which measures the center of mass of the dFC spectrum, with higher values indicating greater energy concentrated at higher frequencies; (b) spectral spread (SPR), which measures the bandwidth of the dFC spectrum; (c) spectral skewness (SKW), which measures the symmetry of the power spectral density, with positive (negative) values indicating positive (negative) skewness; and (d) spectral kurtosis (KURT), which measures the distribution of frequencies around the spectral centroid, with higher values indicating dFC frequencies more highly clustered around the spectral centroid (centroid interpreted as center); Chiang teaches at Page 11 Para 1 teaches Seven other features in the frequency domain were considered: (a) dominant frequency (PEAK), which is the dominant frequency of dFC oscillations, calculated as the peak with the largest average power in its bin [39]; (b) spectral crest (CREST), which measures the peakiness of the power spectral density].
It would have been prima facie obvious skill in the art, at the time of effective filing, to combine the references of Heldman, Howard with the frequency domain features of Chiang with the motivation to increase sensitivity for disease detection.
Claim 7 is rejected under 35 U.S.C. 103(a) as being unpatentable over Heldman, Howard as applied to claim 1 above, and further in view of Rolley et al (US Publication No. 20160158600).
Regarding Claim 7
Heldman/Howard teach the method of claim 1,
Heldman/Howard do not teach further comprising detecting by the processor changes to the plurality of physioloqical signals of the physioloqical screening data during a pre-exertion activity, during an exertion activity including the at least one exertion, and during a post-exertion activity of the predetermined sequence of activities.
Rolley teaches further comprising detecting by the processor changes to the plurality of physioloqical signals of the physioloqical screening data during a pre-exertion activity, during an exertion activity including the at least one exertion, and during a post-exertion activity of the predetermined sequence of activities [Rolley at Para. 0063 teaches for example, in one embodiment, the system 10 may include wearable sensors that can be attached to the body or is contained within a particular material worn as clothing or an attachment to the attire of the patron. In addition, the system 10 may include a portable EEG system that attaches and provides ongoing data of the frequency of the brain waves prior to/during and after training sessions; Rolley at Para. 0075 teaches in the illustrated embodiment, the exercise sequence module 64 receives data indicative of a fitness activity being performed by the user and generates a current exercise sequence as a function of the received data. In addition, the exercise sequence module 64 may compare the current exercise sequence with a planned exercise sequence associated with the patron and determine a condition and/or quality of the patron's fitness activity based on the current and planned exercise sequences].
It would have been prima facie obvious skill in the art, at the time of effective filing, to combine the references of Heldman, Howard with the activities of Rolley with the motivation to improve an individual's fitness training efforts and better manage the risk of potential injury.
Claim 8 is rejected under 35 U.S.C. 103(a) as being unpatentable over Heldman, Howard as applied to claim 1 above, and further in view of Spurlock et al (US Publication No. 20190108915).
Regarding Claim 8
Heldman/Howard teach the method of claim 1,
Heldman/Howard do not teach wherein the machine learning model is a probabilistic model such that the output defines a number between 0 and 1, wherein 0 predicts a minimal probability of a positive diagnosis of the disorder by the individual being screened.
Spurlock teaches wherein the machine learning model is a probabilistic model such that the output defines a number between 0 and 1, wherein 0 predicts a minimal probability of a positive diagnosis of the disorder by the individual being screened [Spurlock at Para. 0080 teaches FIG. 12 gives probability calls from machine learning experiments using mRNA or annotated lncRNA datasets. Cross-sectional expression data from patients at the time of diagnosis but before treatment (MS-NAÏVE) and established MS patients (MS-EST) sub-divided into those receiving glatiramer acetate and those receiving natalizumab. Machine learning scores are determined for MS and reported on a scale from 0 to 1].
It would have been prima facie obvious skill in the art, at the time of effective filing, to combine machine learning of Heldman, Howard with the probability of Spurlock with the motivation to improve disease outcomes.
Claim 10 is rejected under 35 U.S.C. 103(a) as being unpatentable over Heldman, Howard, JHA as applied to claim 1 above, and further in view of CARLINI et al (Foreign Publication WO-2020092786-A1).
Regarding Claim 10
Heldman/Howard/JHA teach the method of claim 2,
Heldman/Howard/JHA do not teach wherein the plurality of physioloqical signals and the plurality of sample signals include physiological, motion, and mechano-acoustic signals associated with a symptom of the disorder.
CARLINI teaches wherein the plurality of physioloqical signals and the plurality of sample signals include physiological, motion, and mechano-acoustic signals associated with a symptom of the disorder [CARLINI at Page 31-32 Lines 31-32,1 teaches the chest EES is mounted on the chest to record electrocardiograms (ECGs), mechano-acoustic signals, and skin temperature].
It would have been prima facie obvious skill in the art, at the time of effective filing, to combine the references of Heldman, Howard, JHA with the signals of CARLINI with the motivation to improve neonatal and pediatric care.
Claims 12-14 are rejected under 35 U.S.C. 103(a) as being unpatentable over Heldman, Howard as applied to claim 1 above, and further in view of CARLINI et al (Foreign Publication WO-2020092786-A1).
Regarding Claim 12
Heldman/Howard teach the method of claim 1,
Heldman/Howard do not teach wherein the sensor system includes a first sensor worn on a chest of the individual to monitor movement and gait patterns, respiratory dynamics, and heart dynamics of the individual, and a second sensor worn on a finger of the individual including a PPG sensing device.
CARLINI teaches wherein the sensor system includes a first sensor worn on a chest of the individual to monitor movement and gait patterns, respiratory dynamics, and heart dynamics of the individual, and a second sensor worn on a finger of the individual including a PPG sensing device [CARLINI at Page 31 Lines 7-10 teaches FIG. 6A schematically shows a functional block diagram of core components of an apparatus including two time-synchronized EES including analog-front-end for ECG processing, 3-axis accelerometer, thermometer IC, and the BLE SoC for the Chest EES and pulse oximeter IC, thermometer, and the BLE SoC for the Limb EES. Specifically, the apparatus as shown in FIG; CARLINI at Page 17 Lines 24-27 teaches as shown in FIG. 2A, the sensor member 163 of the extremity sensor system 150 includes a PPG sensor located within a sensor footprint, which has an optical source having an infrared (IR) light emitting diode (LED) 161 and a red LED 162, and an optical detector (PD) electrically coupled to the IR LED 161 and the red LED 162.].
It would have been prima facie obvious skill in the art, at the time of effective filing, to combine the references of Heldman, Howard with the signals of CARLINI with the motivation to improve neonatal and pediatric care.
Regarding Claim 13
Heldman/Howard/CARLINI teach the method of claim 12,
Heldman/Howard/CARLINI further teach wherein the first sensor measures acceleration, ECG, and a first temperature, and the second sensor measures blood-oxygen and a second temperature [CARLINI at Page 33 Lines 27-30 teaches the Chest EES measures ECGs, the chest movement through the accelerometer, and skin temperature each sampled at 504, 100, and 5 Hz, respectively. The Limb EES measure PPGs and skin temperature sampled at 100 and 5 Hz, respectively].
Regarding Claim 14
Heldman/Howard teach the method of claim 1,
Heldman/Howard do not teach wherein the sensor system includes a motion sensor defining an accelerometer and a photopletysmography (PPG) sensor, such that the plurality of physiological signals includes mechano-acoustic signals recorded by the accelerometer and blood oxygen levels recorded by the PPG sensor.
CARLINI teaches wherein the sensor system includes a motion sensor defining an accelerometer and a photopletysmography (PPG) sensor, such that the plurality of physiological signals includes mechano-acoustic signals recorded by the accelerometer and blood oxygen levels recorded by the PPG sensor [CARLINI at Page 31 Lines 12-21 teaches The Chest EES includes an ECG sensing unit, a motion sensing unit through a 3-axial accelerometer (BMI160, Bosch Sensortec), and a clinical-grade thermometer (MAX30205, Maxim Integrated). The ECG sensing unit includes two gold plated electrodes, an instrumentation amplifier, analog filters, and amplifiers, and a BLE SoC (nRF52832, Nordic Semiconductor). Remained for black PDMS. Data acquisition of the motion sensing by the accelerometer is controlled by BLE SoC through Serial Peripheral Interface (SPI) communication protocol, while the temperature data by the thermometer is acquired through the Inter-integrated Circuit (I2C) communication protocol. The Limb EES includes an integrated pulse oximetry module (MAX30101, Maxim Integrated) for measuring blood oxygenation (Sp02) and the thermometer (MAX30205, Maxim Integrated)].
It would have been prima facie obvious skill in the art, at the time of effective filing, to combine the references of Heldman, Howard with the signals of CARLINI with the motivation to improve neonatal and pediatric care.
Claim 15 is rejected under 35 U.S.C. 103(a) as being unpatentable over Heldman, Howard as applied to claim 1 above, and further in view of Antonelli et al (“Comparison between the Airgo™ Device and a Metabolic Cart during Rest and Exercise”).
Regarding Claim 15
Heldman/Howard teach the method of claim 1,
Heldman/Howard do not teach wherein the disorder is a COVID-19 infection, and the plurality of physiological signals includes a heart signal, and a change in heart signal between activities in the predetermined sequence of activities is extracted by the processor as a feature for the machine learning model, and the plurality of physiological signals further includes an acceleration signal indicative of a respiration rate of the individual.
Antonelli teaches wherein the disorder is a COVID-19 infection, and the plurality of physiological signals includes a heart signal, and a change in heart signal between activities in the predetermined sequence of activities is extracted by the processor as a feature for the machine learning model, and the plurality of physiological signals further includes an acceleration signal indicative of a respiration rate of the individual individual [Antonelli at Page 3 Para 3 teaches Test under physical exercise: execution of a cardiopulmonary exercise test on the Ergoline cycle ergometer 800S, followed by a recovery period. A symptom-limited incremental exercise test was performed and designed to achieve a maximum load in 10 ± 2 min in each subject wearing