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 Claims
This action is in reply to the application filed on January 16, 2025.
2. Claim(s) 1-20 are currently pending and have been examined.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more. Based upon consideration of all of the relevant factors with respect to the claims as a whole, the claims are directed to non-statutory subject matter which do not include additional elements that are sufficient to amount to significantly more than the judicial exception because of the following analysis:
Independent Claim(s) 1, 8 and 15 are directed to an abstract idea consisting of a methods and systems comprising algorithmic analysis of medical time-series data to predict a disease risk and decide a treatment.
Independent Claim 1 recites “receiving, a plurality of physiological measurements of a target patient and corresponding to one or more urinalysis variable values; determining a time series of physiological measurements from the received plurality of physiological measurements; based on the time series of physiological measurements, determining wavelet transform information corresponding at least partially to one or both of: (a) at least one wavelet set of data associated with a frequency representation of a first set of content, wherein the first set of content corresponds to a first portion of the time series of physiological measurements; and (b) two or more time scale representations of data associated with the frequency representation and/or with a second set of content, wherein the second set of content corresponds to a second portion of the time series of physiological measurements; and utilizing analysis information corresponding at least partially to the time series of physiological measurements, the wavelet transform information, an algorithmic predictor, or any combination thereof to generate a forecast of the a likelihood of urolithiasis for the target patient over a future time interval, wherein: based at least partially on the generated forecast and the likelihood of urolithiasis for the target patient over the future time interval, an intervening action is initiated to administer a particular treatment procedure to the target patient in association with treating a particular condition associated with the generated forecast and with the likelihood of urolithiasis for the target patient over the future time interval.”
Independent Claim 8 recites “receiving, a plurality of physiological measurements of a target patient and corresponding to one or more urinalysis variable values; determining a time series of physiological measurements from the received plurality of physiological measurements; based on the time series of physiological measurements, determining wavelet transform information corresponding at least partially to one or both of: (a) at least one wavelet set of data associated with a frequency representation of a first set of content, wherein the first set of content corresponds to a first portion of the time series of physiological measurements; and (b) two or more time scale representations of data associated with the frequency representation and/or with a second set of content, wherein the second set of content corresponds to a second portion of the time series of physiological measurements; and utilizing analysis information corresponding at least partially to the time series of physiological measurements, the wavelet transform information, an algorithmic predictor, or any combination thereof to generate a forecast of the a likelihood of urolithiasis for the target patient over a future time interval, wherein: based at least partially on the generated forecast and the likelihood of urolithiasis for the target patient over the future time interval, an intervening action is initiated to administer a particular treatment procedure to the target patient in association with treating a particular condition associated with the generated forecast and with the likelihood of urolithiasis for the target patient over the future time interval.”
Independent Claim 15 recites “receiving, a plurality of physiological measurements of a target patient and corresponding to one or more urinalysis variable values; determining a time series of physiological measurements from the received plurality of physiological measurements; based on the time series of physiological measurements, determining wavelet transform information corresponding at least partially to one or both of: (a) at least one wavelet set of data associated with a frequency representation of a first set of content, wherein the first set of content corresponds to a first portion of the time series of physiological measurements; and (b) two or more time scale representations of data associated with the frequency representation and/or with a second set of content, wherein the second set of content corresponds to a second portion of the time series of physiological measurements; and utilizing analysis information corresponding at least partially to the time series of physiological measurements, the wavelet transform information, an algorithmic predictor, or any combination thereof to generate a forecast of the a likelihood of urolithiasis for the target patient over a future time interval, wherein: based at least partially on the generated forecast and the likelihood of urolithiasis for the target patient over the future time interval, an intervening action is initiated to administer a particular treatment procedure to the target patient in association with treating a particular condition associated with the generated forecast and with the likelihood of urolithiasis for the target patient over the future time interval.”
The limitations of Claims 1, 8 and 15, as drafted, under its broadest reasonable interpretation, covers the performance of a Mental Process which are concepts performed in the human mind (including an observation, evaluation, judgment, opinion), Certain Methods Of Organizing Human Activity which are concepts performed by managing personal behavior, relationships or interactions between people (including fundamental economic principles, commercial or legal interactions, social activities, teaching, and following rules or instructions) and Mathematical Concepts which are concepts performed that encompasses mathematical relationships, mathematical formulas or equations, and mathematical calculations, but for the recitation of generic computer components. That is, other than reciting, “one processor of the one or more hardware processors associated with an electronic digital memory at a medical records computer system” nothing in the claim element precludes the step from practically being performed by evaluating medical data and choosing treatment using calculations. For example, but for the “processor” language, “receiving” in the context of this claim encompasses the user manually retrieving a plurality of physiological measurements of a target patient and corresponding to one or more urinalysis variable values. Similarly, the determining, a time series of physiological measurements from the received plurality of physiological measurements, covers performance of evaluating medical data and choosing treatment using calculations, but for the recitation of generic computer components. If a claim limitation, under its broadest reasonable interpretation, covers performance of evaluating medical data and choosing treatment using calculations, but for the recitation of generic computer components, then it falls within the “Mental Process, Certain Methods of Organizing Human Activity and Mathematical Concepts” 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 using a “one processor of the one or more hardware processors associated with an electronic digital memory at a medical records computer system” to perform all of the “receiving, determining, utilizing and generating” steps. The “one processor of the one or more hardware processors associated with an electronic digital memory at a medical records computer system” is/are recited at a high-level of generality (i.e., as a generic processor performing a generic computer function) of executing computer-executable instructions for implementing the specified logical function(s) 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.
Claim 1 has the following additional elements (i.e., one processor of the one or more hardware processors associated with an electronic digital memory at a medical records computer system). Claim 8 has the following additional elements (i.e., one processor of the one or more hardware processors associated with an electronic digital memory at a medical records computer system). Claim 15 has the following additional elements (i.e., one processor of the one or more hardware processors associated with an electronic digital memory at a medical records computer system). Looking to the specification, these components are described at a high level of generality (see paragraph 68; a portion of computing system 120 may be embodied on user interface 142, application 140, and/or EHR system(s) 160.In one embodiment, system 120 comprises one or more computing devices, such as a server, desktop computer, laptop, or tablet, cloud-computing device or distributed computing architecture, a portable computing device such as a laptop, tablet, ultra-mobile P.C., or a mobile phone). The use of a general-purpose computer, taken alone, does not impose any meaningful limitation on the computer implementation of the abstract idea, so it does not amount to significantly more than the abstract idea. Also, although the claims add “[storage]” steps, it is only considered as insignificant extrasolution activity. Looking at the limitations as an ordered combination adds nothing that is not already present when looking at the elements individually. The combination of elements does not indicate a significant improvement to the functioning of a computer or any other technology and their collective functions merely provide a conventional computer implementation of the abstract idea. Furthermore, the additional elements or combination of elements in the claims, other than the abstract idea per se, amount to no more than a recitation of generally linking the abstract idea to a particular technological environment or field of use, as the courts have found in Parker v. Flook. Therefore, there are no limitations in the claims that transform the judicial exception into a patent eligible application such that the claims amount to significantly more than the judicial exception.
It is worth noting that the above analysis already encompasses each of the current dependent claims (i.e., claims 2-7, 9-14 and 16-20). Particularly, each of the dependent claims also fails to amount to “significantly more’ than the abstract idea since each dependent claim is directed to a further abstract idea, and/or a further conventional computer element/function utilized to facilitate the abstract idea. Accordingly, none of the current claims implements an element—or a combination of elements—directed to an inventive concept (e.g., none of the current claims is reciting an element—or a combination of elements—that provides a technological improvement over the existing/conventional technology). These information characteristics do not change the fundamental analogy to the abstract idea grouping of “Mental Process, Certain Methods of Organizing Human Activity and Mathematical Concepts,” and, when viewed individually or as a whole, they do not add anything substantial beyond the abstract idea. Furthermore, the combination of elements does not indicate a significant improvement to the functioning of a computer or any other technology. Therefore, the claims when taken as a whole are ineligible for the same reasons as the independent claims.
Claims 1-20 are therefore not drawn to eligible subject matter as they are directed to an abstract idea without significantly more.
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.
Claims 1-20 are rejected under 35 U.S.C. 103 as being unpatentable over Pub. No.: US 2011/0313788 A1 to AMLAND et al. in view of Pub. No.: US 2015/0213227 A1 to Vairavan et al. further in view of Pub. No.: US 2016/0183886 A1 KONNO.
Claim 1 recites:
“A system having one or more hardware processors configured to facilitate a plurality of operations, the operations comprising:
Receiving, via at least one processor of the one or more hardware processors associated with an electronic digital memory at a medical records computer system, a plurality of physiological measurements of a target patient and corresponding to one or more urinalysis variable values;
determining a time series of physiological measurements from the received plurality of physiological measurements;
based on the time series of physiological measurements, determining wavelet transform information corresponding at least partially to one or both of: (a) at least one wavelet set of data associated with a frequency representation of a first set of content, wherein the first set of content corresponds to a first portion of the time series of physiological measurements; and (b) two or more time scale representations of data associated with the frequency representation and/or with a second set of content, wherein the second set of content corresponds to a second portion of the time series of physiological measurements; and
utilizing analysis information corresponding at least partially to the time series of physiological measurements, the wavelet transform information, an algorithmic predictor, or any combination thereof to generate a forecast of the a likelihood of urolithiasis for the target patient over a future time interval, wherein:
based at least partially on the generated forecast and the likelihood of urolithiasis for the target patient over the future time interval, an intervening action is initiated to administer a particular treatment procedure to the target patient in association with treating a particular condition associated with the generated forecast and with the likelihood of urolithiasis for the target patient over the future time interval.”
Amland et al. teaches:
A system having one or more hardware processors configured to facilitate a plurality of operations. Amland describes an exemplary computing system environment including a server whose components comprise a processing unit, internal system memory, and a system bus coupling various system components including a database cluster, operating in a networked medical information environment and executing program modules (paragraphs 0018–0023).
Receiving, via at least one processor of the one or more hardware processors associated with an electronic digital memory at a medical records computer system, a plurality of physiological measurements of a target patient and corresponding to one or more urinalysis variable values. Amland explains that its method includes receiving patient data for a patient, wherein the patient data is received from an electronic medical record, and that clinically relevant data used as training data may come from hospital electronic medical records and laboratory test results; its order sets include urinalysis tests among diagnostic orders, indicating that urine-based laboratory data are part of the EMR environment (paragraphs 0004, 0033, 0038–0039; claim 4; FIG. 5).
Determining a time series of physiological measurements from the received plurality of physiological measurements. Amland’s FIG. 4 shows lab results graphed over multiple days at specific timestamps (for example, BUN, creatinine clearance, creatinine at 02/23 07:00, 02/23 14:00, 02/24 07:00), indicating repeated measurements of lab values over time; Amland further states that a readmission risk score may be recalculated over the length of hospitalization based on updated patient data, implying use of a time-series of measurements (paragraph 0011; paragraphs 0030–0031; FIG. 4).
Utilizing analysis information and an algorithmic predictor to generate a forecast of a likelihood over a future time interval, wherein an intervening action is initiated. Amland discloses computing a readmission risk score representing a probability of readmission over a predetermined period (for example, within 7, 30, 60, 90 days after discharge) using prediction models such as logistic regression, and using that risk to drive clinical interventions and care plan modifications including recommending alternate therapies, performing additional studies, extending the patient’s length of stay, and planning outpatient follow-up (paragraphs 0003–0004, 0028–0032; claims 1, 6, 9, 12–14; FIGS. 4–6).
Amland et al. fails to explicitly teach:
that the plurality of physiological measurements corresponds specifically to one or more urinalysis variable values as the primary predictive variables
based on the time series of physiological measurements, determining wavelet transform information, including a wavelet-based frequency representation associated with a first portion of the time series and two or more time-scale representations associated with that frequency representation and/or a second portion of the time series
using such wavelet-domain information, together with the time series itself, as analysis information in an algorithmic predictor specifically configured to generate a forecast of a likelihood of urolithiasis over the claimed future time interval
Vairavan et al. teaches:
Vairavan describes a medical modeling system in which at least one processor is programmed to receive measurements of a plurality of predictive variables for a patient and calculate the risk of a physiological condition by applying the received measurements to at least one model (including a logistic regression model) using the plurality of predictive variables and outputting an indication of risk to a clinician. The predictive variables include lab tests and physiological variables such as creatinine, BUN, bilirubin, vital signs, and urine-related variables, and are measured over time so that each patient record includes a time series of measurements over a defined period with specified sampling intervals (for example, hourly measurements over 48 hours). A clinical decision system uses the calculated risk to support planning, scheduling, and allocation of ICU resources (Abstract; paragraphs 0006–0008, 0011–0012, 0045–0049; FIG. 3).
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to include systems/methods as taught by Vairavan et al. within the systems/methods as taught by Amland et al. with the motivation of improving Amland’s readmission-risk decision-support system by incorporating explicit time-series modeling of physiological and laboratory measurements (including urine-related measures) using advanced algorithmic predictors, so as to generate patient-specific forecasts of future disease risks from temporal physiological data and to use those forecasts to drive risk-based clinical interventions as described by Vairavan et al.
Amland et al. and Vairavan et al. fail to explicitly teach:
determining wavelet transform information from the time series of physiological measurements, including a wavelet-based frequency representation for a first portion of the time series and two or more time-scale representations associated with that frequency representation and/or a second portion of the time series,
using such wavelet-domain information, together with the time series itself, as analysis information in the algorithmic predictor particularly configured to generate a forecast of the likelihood of urolithiasis over the claimed future time interval.
Konno teaches:
Konno describes a biological information predicting apparatus including a biological parameter acquiring section configured to acquire biological parameters over time and a biological information predicting section configured to predict a future trend of a second biological parameter based on a future prediction model and a history of values of a first biological parameter, the model defining a relationship between changes in the first and second parameters, and a notifying section that provides a notification based on the prediction. Konno explains that the biological parameters and future prediction model are not limited to the specific examples described and may be defined using various parameters and model structures, allowing the use of different time-series-derived quantities from histories to drive future-risk prediction (Abstract; paragraphs 0008–0010, 0018, 0076–0079, 0080–0083).
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to include systems/methods as taught by Konno with the systems/methods as taught by Amland et al. and Vairavan et al. with the motivation of using Konno’s explicit history-based future-trend prediction framework and flexible definition of biological parameters and models to justify computing time-frequency and multi-scale descriptors—such as wavelet-derived frequency representations and time-scale-dependent features—from urinalysis-based physiological time series and supplying such wavelet-domain analysis information as inputs to the combined Amland/Vairavan predictive models in order to enhance future urolithiasis-risk forecasting while still operating in an electronic-medical-record-linked clinical decision-support environment.
Claim 2 recites:
“The system of claim 1, wherein the operations further comprise determining content corresponding to one or both of an RQA recurrence rate and a set of Holder exponents.”
Amland et al. teaches that clinically relevant patient data, including laboratory test results obtained from hospital electronic medical records, are retrieved and used in statistical models such as logistic regression to generate a readmission-risk prediction model that calculates a risk score from patient-specific data, and that these scores may be recalculated over time as new measurements are obtained (paragraphs 0003–0004, 0028–0036).
Amland et al. fails to explicitly teach:
determining content corresponding to an RQA recurrence rate from physiological-measurement time series
determining content corresponding to a set of Holder exponents from physiological-measurement time series
using recurrence quantification analysis or Holder-exponent-based descriptors as part of the extracted content from patient time-series data
Vairavan et al. teaches selecting time-series-based predictor variables and derived features from repeated measurements over time and using them in sophisticated modeling frameworks such as logistic regression and hidden Markov models to predict clinical outcomes, and notes that feature engineering on time-series data is used to improve prediction performance (paragraphs 0012–0015, 0045–0049).
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to include systems/methods as taught by Vairavan et al. within the systems/methods as taught by Amland et al. with the motivation of enriching the time-series feature set used by the algorithmic predictor with additional quantitative descriptors derived from the temporal structure of the physiological signals, consistent with the known practice of extracting time-series features for use in clinical risk models as taught by Vairavan et al.
Konno explains that the biological parameters and future prediction model are not limited to the specific examples described and may be defined using various parameters and model structures, allowing designers to extract and use different numeric quantities from parameter histories to characterize trends and future risk (paragraphs 0080–0083).
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to include systems/methods as taught by Konno with the systems/methods as taught by Amland et al. and Vairavan et al. with the motivation of defining additional time-series characterization metrics—such as RQA recurrence rates and Holder exponents—as allowable content derived from physiological-measurement histories and using those metrics alongside more conventional features in the predictive models to capture complex temporal patterns relevant to long-term urolithiasis risk.
Claim 3 recites:
“The system of claim 2, wherein the operations further comprise utilizing one or both of the RQA recurrence rate and at least a subset of the set of Holder exponents in connection with the algorithmic predictor.”
Amland et al. teaches using clinically relevant data in an algorithmic predictor such as a logistic regression model to compute a readmission-risk score and then using that score to influence treatment recommendations (paragraphs 0003–0004, 0034–0036, 0040–0043).
Amland et al. fails to explicitly teach:
utilizing an RQA recurrence rate in connection with the algorithmic predictor
utilizing at least a subset of a set of Holder exponents in connection with the algorithmic predictor
configuring the algorithmic predictor to accept RQA- and Holder-based inputs as specific non-linear time-series features
As described above, Vairavan et al. teaches that predictor variables include time-series laboratory and physiological measures (including urine-related variables) and that these variables, possibly transformed or summarized over time, are used in logistic-regression and HMM models to generate risk predictions, with flexibility in feature selection and transformation to improve performance (paragraphs 0012–0015, 0045–0049).
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to include systems/methods as taught by Vairavan et al. within the systems/methods as taught by Amland et al. with the motivation of treating RQA recurrence rates and Holder-exponent-based quantities simply as additional time-series-derived predictor variables used in connection with the existing logistic-regression and related algorithmic predictors, as a straightforward extension of the known practice of enriching clinical models with more informative temporal features.
Konno’s framework for using histories of one biological parameter to predict future values and risk levels of another parameter, with flexibility in how models and parameters are defined, supports the notion of plugging in different numeric descriptors of the histories (such as multi-scale or recurrence-based measures) into the prediction model (paragraphs 0010, 0076–0079, 0080–0083).
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to include systems/methods as taught by Konno with the systems/methods as taught by Amland et al. and Vairavan et al. with the motivation of utilizing RQA recurrence rates and Holder-exponent-based values as part of the numeric history-based features connected to the algorithmic predictor, thereby implementing Konno’s general teaching that various derived quantities from biological histories can be fed into future-prediction models to refine risk estimation.
Claim 4 recites:
“The system of claim 3, wherein one or both of a first set of data corresponding to the RQA recurrence rate and a second set of data corresponding to the subset of the set of Holder exponents are utilized in a machine-learning electronic model corresponding to the algorithmic predictor and/or to a logistic regression model.”
Amland et al. teaches that a logistic regression model is built using retrieved clinically relevant data and that a readmission-risk prediction model is generated using the output from the logistic regression model, describing a learned model implemented on computer hardware functioning as a machine-learning electronic model (paragraphs 0003–0004, 0034–0036; claim 18).
Amland et al. fails to explicitly teach:
that a first set of data corresponding to an RQA recurrence rate is utilized in a machine-learning electronic model
that a second set of data corresponding to a subset of a set of Holder exponents is utilized in a machine-learning electronic model
that such first and second data sets are used as specific input feature groups to a logistic regression or related machine-learning model
Vairavan et al. teaches that its mortality logistic-regression model is fitted to training data using a parameter-estimation technique and that various physiological and laboratory predictors are used as input data vectors to the model (paragraphs 0045–0049).
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to include systems/methods as taught by Vairavan et al. within the systems/methods as taught by Amland et al. with the motivation of treating RQA-based and Holder-based data sets simply as additional components of the input feature vectors supplied to a logistic regression or related machine-learning electronic model, as an obvious extension of using multiple time-series-derived predictor variables in such models to capture richer temporal behavior.
Konno indicates that the future prediction model can take various parameters and forms and is implemented in a biological information predicting apparatus, with processes that may be implemented as computer programs operating on the apparatus, thereby supporting use of machine-learning-type models that ingest feature sets derived from histories (paragraphs 0076–0079, 0080–0084).
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to include systems/methods as taught by Konno with the systems/methods as taught by Amland et al. and Vairavan et al. with the motivation of implementing the algorithmic predictor as a machine-learning electronic model (including logistic regression) that uses RQA and Holder-exponent-based data sets as part of its learned input feature space, consistent with the general teaching of using flexible, history-based models to predict future biological trends and risk levels.
Claim 5 recites:
“The system of claim 1, wherein the operations further comprise utilizing the algorithmic predictor to generate a particular forecast of the likelihood of urolithiasis for the target patient over the future time interval.”
Amland et al. teaches utilizing an algorithmic predictor (for example, a logistic regression-based model) to generate a readmission-risk score representing a probability of readmission for the patient over a specified future time interval (for example, within 7, 30, 60, 90 days after discharge) and using that score to guide clinical interventions (paragraphs 0003–0004, 0028–0030, 0034–0036).
Amland et al. fails to explicitly teach:
that the particular forecast generated by the algorithmic predictor is a likelihood of urolithiasis
that the forecasted future event is urolithiasis occurrence rather than hospital readmission
Vairavan et al. teaches using logistic-regression and hidden Markov models to generate a risk of a physiological condition such as ICU mortality or survival, with that forecast supplied to a clinical decision system (Abstract; paragraphs 0006–0008, 0045–0049).
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to include systems/methods as taught by Vairavan et al. within the systems/methods as taught by Amland et al. with the motivation of applying the same general predictive modeling framework (an algorithmic predictor generating a disease-risk forecast over a time interval) to a different but closely analogous target outcome—namely, the likelihood of urolithiasis for the patient over a chosen future interval—since both readmission and disease-specific events are routine subjects of electronic-medical-record-based risk prediction.
Konno’s biological information predicting apparatus predicts future trends and risk levels of a second biological parameter based on histories of a first parameter and uses that prediction to trigger notifications, demonstrating the general concept of forecasting a particular health-related quantity and acting upon it (paragraphs 0010, 0076–0079).
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to include systems/methods as taught by Konno with the systems/methods as taught by Amland et al. and Vairavan et al. with the motivation of configuring the algorithmic predictor to output a specific forecast of urolithiasis likelihood, analogous to Konno’s forecasting of future abnormal conditions, and to use that disease-specific forecast to drive the same types of intervention workflows that Amland and Vairavan already tie to risk predictions.
Claim 6 recites:
“The system of claim 1, wherein each subsequent measurement in a sequence of the plurality of physiological measurements is obtained after at least a minimum time interval has elapsed from a previous measurement in the sequence of the plurality of physiological measurements.”
Amland et al. discloses multiple lab measurements graphed over several days at distinct timestamps (for example, 02/23 07:00, 02/23 14:00, 02/24 07:00, 02/24 14:00, 02/25 07:00), indicating that lab values are measured at successive times and stored as multiple data points for a patient; it also explains that the readmission-risk score may be recalculated over the length of hospitalization based on updated patient data, which implies repeated measurement events over time (paragraph 0011; paragraphs 0030–0031; FIG. 4).
Amland et al. fails to explicitly teach:
that the plurality of physiological measurements is described as a sequence of measurements
that each subsequent measurement is obtained after at least a minimum time interval has elapsed from a previous measurement in the sequence, with any explicit minimum interval defined.
Vairavan et al. describes that the record for an ICU patient includes one or more measurements over time, typically a plurality of measurements over time (a time series) for each variable spanning a period of hours (for example, 48 hours), with vital signs and lab tests measured every hour, and explains that each time at least one predictor variable is measured, or in response to a periodic event, the mortality logistic-regression model updates the prediction using the most recent measurements (paragraphs 0047–0049).
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to include systems/methods as taught by Vairavan et al. within the systems/methods as taught by Amland et al. with the motivation of explicitly treating repeated clinical measurements of physiological variables as an ordered time-series sequence with a minimum sampling interval between successive measurements (for example, hourly or another designed minimum interval) to support systematic time-series modeling and periodic risk updates as in the ICU mortality-risk framework.
Claim 7 recites:
“The system of claim 1, wherein the plurality of physiological measurements correspond to a plurality of measured specific gravities of urine, and wherein the time series of physiological measurements comprises at least 60 time stamped physiological measurements.”
Amland et al. indicates that clinically relevant data include laboratory test results obtained from hospital electronic medical records and that urinalysis tests appear among diagnostic orders, showing that urine-related lab results are part of the patient’s data used for decision support; it also shows multiple lab measurements with timestamps over several days, indicating that substantial numbers of time-stamped measurements may be collected over an episode of care (paragraph 0033; paragraph 0011; FIGS. 4–5).
Amland et al. fails to explicitly teach:
that the plurality of physiological measurements correspond to a plurality of measured specific gravities of urine as the particular physiological variable set
that the time series of physiological measurements comprises at least 60 time-stamped physiological measurements
Vairavan et al. identifies urine-related variables among its predictors and describes that predictor variables are measured over time and that for each ICU patient, vital signs and lab tests are measured at regular intervals over a defined period (for example, hourly over 48 hours), naturally yielding dozens of time-stamped measurements per variable (FIG. 3; paragraphs 0045–0049).
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to include systems/methods as taught by Vairavan et al. within the systems/methods as taught by Amland et al. with the motivation of selecting a urine-concentration–related measurement such as urine-specific gravity as the primary physiological variable for a urolithiasis-focused risk model and collecting a sufficiently large number of time-stamped measurements (for example, at least 60) as a routine design choice to ensure adequate temporal resolution for time-series and wavelet-based analysis, consistent with the multi-measurement sampling regimes used in clinical time-series risk models.
Claims 8–14
As per Claims 8-14, Claims 8-14 are directed to a non-transitory media. Claims 8-14 recite the same or substantially similar limitations as those addressed above for Claims 1-7 as taught by Amland et al., Vairavan et al. and Konno. Claims 8-14 are therefore rejected for the same reasons as set forth above for Claims 1-7 respectively.
Claims 15–20
As per Claims 15-20, Claims 15-20 are directed to a computer-implemented method. Claims 15-20 recite the same or substantially similar limitations as those addressed above for Claims 1-6 as taught by Amland et al., Vairavan et al. and Konno. Claims 15-20 are therefore rejected for the same reasons as set forth above for Claims 1-6 respectively.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
US 20080125666 A1: Biological data, such as human heart rate data, is acquired and processed in a non-linear manner to facilitate an assessment of the physiological state of the subject, and/or to assist in predicting incipient disorders or instability. Determinism, laminarity and recurrence measures are derived for a rolling sample of a time series of said data. The recurrence measure can be the Euclidean threshold (.epsilon..sub.thresh) at a given recurrence rate. A representation, such a colour coded matrix or multi-dimensional vector, is formed from a combination of the derived determinism, laminarity and recurrence measures. The representation can then be analysed to detect indicators of physiological instability, such as arrhythmia, or to discriminate between arrhythmias. The analysis may be performed visually, or in an automated manner in real time, such as in an ambulatory or implanted device, or post hoc by a bedside monitor.
US 20090098553 A1: This invention relates to methods for determining the presence of cancer in a subject based on the analysis of the expression levels of an under-expressed tumour marker (TM) and at least one other TM. Specifically, this invention relates to the determination of a cancer, particularly bladder cancer, by performing ratio, regression or classification analysis of the expression levels of at least one under-expressed TM, particularly an under-expressed bladder TM (BTM), and at least one over-expressed TM, particularly an over-expressed BTM. In various aspects, the invention relates to kits and devices for carrying out these methods.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to EDWARD B WINSTON III whose telephone number is (571)270-7780. The examiner can normally be reached M-F 1030 to 1830.
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, Robert Morgan can be reached at (571) 272-6773. 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.
/E.B.W/ Examiner, Art Unit 3683
/ROBERT W MORGAN/ Supervisory Patent Examiner, Art Unit 3683