DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Status of Application
This action is in reply to the reply received March 10, 2026 (hereinafter “Reply”).
Claims 1-19 are canceled.
Claims 20-38 are amended.
Claims 20-39 are pending.
Claim Rejections - 35 U.S.C. § 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 20-39 are rejected under 35 U.S.C. § 101 because the claimed invention is directed to non-statutory subject matter. Claims 20-39 are directed to an abstract idea without significantly more as required by the Alice test as discussed below.
Step 1
Claims 20-39 are directed to a process, machine, manufacture, or composition of matter.
Step 2A
Claims 20-39 are directed to abstract ideas, as explained below.
Prong one of the Step 2A analysis requires identifying the specific limitation(s) in the claim under examination that the examiner believes recites an abstract idea; and determining whether the identified limitation(s) falls within at least one of the groupings of abstract ideas of mathematical concepts, mental processes, and certain methods of organizing human activity.
The claims recite the following limitations that are directed to abstract ideas. Claim 20 recites receiving a medical report of a patient associated with a local healthcare site; analysing said medical report for an outcome of a complication of the patient by a trained machine learning model trained on a general cohort comprising multiple patients from multiple different healthcare sites, thereby obtaining a complication outcome; receiving a true outcome of the complication; and updating the trained machine learning model dynamically based on the true outcome of the complication to become a locally trained machine learning model configured to predict an outcome of a complication of a patient associated with the local healthcare site. Claims 21-39 further specify characteristics of these identified abstract ideas or characteristics of the data used thereby.
The term “machine learning model” includes a class of algorithms or data structures that can be, but is not required to be, implemented by a machine. To the extent that this term relates to the algorithms or data structures themselves, the term is identified as being part of the abstract idea. To the extent that the claims require a machine to implement the learning model, this aspect will be addressed below as an additional element.
These limitations describe abstract ideas that correspond to concepts identified as abstract ideas by the courts as mental processes—such as concepts performed in the human mind (including an observation, evaluation, judgment, or opinion)—because the claimed features identified above are concepts performed in the human mind (including an observation, evaluation, judgment, or opinion).
These limitations describe abstract ideas that correspond to concepts identified as abstract ideas by the courts as certain methods of organizing human activity—such as fundamental economic principles or practices (including hedging, insurance, mitigating risk), commercial or legal interactions (including agreements in the form of contracts; legal obligations; advertising, marketing or sales activities or behaviors; business relations), managing personal behavior or relationships or interactions between people (including social activities, teaching, and following rules or instructions)—because the claim features identified above manage personal behavior or relationships or interactions between people including teaching and following rules or instructions.
Thus, the concepts set forth in claims 20-39 recite abstract ideas.
Prong two of the Step 2A requires identifying whether there are any additional elements recited in the claim beyond the judicial exception(s), and evaluating those additional elements to determine whether they integrate the exception into a practical application of the exception. “Integration into a practical application” requires an additional element or a combination of additional elements in the claim to apply, rely on, or use the judicial exception in a manner that imposes a meaningful limit on the judicial exception, such that the claim is more than a drafting effort designed to monopolize the exception. Further, “integration into a practical application” uses the considerations laid out by the Supreme Court and the Federal Circuit to evaluate whether the judicial exception is integrated into a practical application, such as considerations discussed in M.P.E.P. § 2106.05(a)-(h).
The claims recite the following additional elements beyond those identified above as being directed to an abstract idea. Claim 20 recites that is method is computer-implemented, a computer system, and a machine learning model. Claim 38 recites a processor. Claim 39 recites a computer.
The identified judicial exception(s) are not integrated into a practical application for the following reasons.
First, evaluated individually, the additional elements do not integrate the identified abstract ideas into a practical application. The additional computer elements identified above—the computer, computer system, machine, and processor—are recited at a high level of generality. Inclusion of these elements amounts to mere instructions to implement the identified abstract ideas on a computer. See M.P.E.P. § 2106.05(f). Further, to the extent that the claims require a machine to implement the machine learning model, this, too, amounts to mere instructions to implement the identified abstract ideas on a computer. See id. To the extent that the claims transform data, the mere manipulation of data is not a transformation. See M.P.E.P. § 2106.05(c). Inclusion of the computing system in the claims amounts to generally linking the use of the judicial exception to a particular technological environment or field of use. See M.P.E.P. § 2106.05(h). Thus, taken alone, the additional elements do not amount to significantly more than a judicial exception.
Second, evaluating the claim limitations as an ordered combination adds nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer or improves any other technology. See M.P.E.P. § 2106.05(a). Their collective functions merely provide an implementation of the identified abstract ideas on a computer system in the general field of use of predicting medical outcomes. See M.P.E.P. § 2106.05(h).
Thus, claims 20-39 recite mathematical concepts, mental processes, or certain methods of organizing human activity without including additional elements that integrate the exception into a practical application of the exception.
Accordingly, claims 20-39 are directed to abstract ideas.
Step 2B
Claims 20-39 do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the additional elements, when considered both individually and as an ordered combination, do not amount to significantly more than the abstract idea.
The analysis above describes how the claims recite the additional elements beyond those identified above as being directed to an abstract idea, as well as why identified judicial exception(s) are not integrated into a practical application. These findings are hereby incorporated into the analysis of the additional elements when considered both individually and in combination. Additional features of these analyses are discussed below.
Evaluated individually, the additional elements do not amount to significantly more than a judicial exception, as discussed above regarding Step 2A, prong two. Thus, taken alone, the additional elements do not amount to significantly more than a judicial exception.
Evaluating the claim limitations as an ordered combination adds nothing that is not already present when looking at the elements taken individually. In addition to the factors discussed regarding Step 2A, prong two, there is no indication that the combination of elements improves the functioning of a computer or improves any other technology. Their collective functions merely amount to mere instructions to implement the identified abstract ideas on a computer.
Thus, claims 20-39, taken individually and as an ordered combination of elements, are not directed to eligible subject matter since they are directed to an abstract idea without significantly more.
Claim Rejections - 35 U.S.C. § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. § 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 20-26, 28-31, and 36-39 are rejected under 35 U.S.C. § 102(a)(1)-(2) as being anticipated by Mortazavi et al. (U.S. Pub. No. 2018/0315507 A1) (hereinafter “Mortazavi”).
Claim 20: Mortazavi, as shown, discloses the following limitations:
receiving, by a computer system, a medical report of a patient associated with a local healthcare site (see at least ¶ [0038]: data were extracted for each admission. Each visit’s dataset consisted of data from admission time to either 24 hours or the start of patient's first procedure, whichever came first; this period of time was believed to be long enough to gather clinically relevant information on the patients to provide an understanding of patient risk prior to the procedure that resulted in the adverse event. Further, this aligned with clinical rounds typically happening every morning and procedures often happening soon after admission. The desired goal, therefore, was to create a dataset and system that would serve as a balance between early enough for appropriate decision making and late enough for considering a wide array of data; see also at least ¶ [0044]: the data were extracted from the EHR data tables shown in FIG. 1, where each VisitID in the patient cohort table had a one-to-many relationship with entries in each of the other tables of the database. The data were organized in seven tables (plus a Rothman Index Scores table), listed in Table I (see FIG. 7). These tables were joined from back-end tables storing data from the front-end of EPIC. The Cohort table contained patient information, including the admission source (e.g. self-referral, transfer from another hospital, transfer from another unit, physician referral), insurance information (e.g. Medicare, private insurance, etc.), and personal information (e.g. age, gender, race if provided). The patient population included 1025 CABG patients, 2539 PCI patients, and 1650 ICD patients. Table II (see FIG. 6) shows the event rates of respiratory failure and infection. Despite the low event rates, these patients were adversely harmed and attributed a significant cost to the hospital [13]. The data extracted were structured data organized in the back-end data warehouse for the EHR system, allowing for quick manipulation of fields for feature extraction; see also at least ¶¶ [0039]-[0043]; see also at least ¶ [0035]: this study used all data available in the EHR from February, 2013 (the go-live date for EPIC at Y-NHH) through September, 2015. As prior data were stored on a different HER system, all visits from this date forward were considered first visits. Methods considered for this work considered data upon patient presentation at admission and collected from then forward; see also at least ¶¶ [0015], [0017], and [0038]);
analysing said medical report for an outcome of a complication of the patient by a computer system comprising a trained machine learning model trained on a general cohort comprising multiple patients from multiple different healthcare sites, thereby obtaining a complication outcome (see at least ¶ [0014]: the research has led to the development of a system for identifying patients undergoing major cardiovascular procedures at risk for postoperative respiratory failure or infection, two costly outcomes as identified by at Y-NHH. The system tackles the challenges of extracting data from a production-level electronic health record provided by EPIC [33] and the tasks necessary in manipulating data for use in machine learning analytic tools. Further, after developing models to predict postoperative complications using preoperative data, the system can generate interpretable measures of risk to help identify the risk category of the patient, as well as the contributing features to risk in order to better provide clinicians with information that might help prevent such adverse events, providing a framework for more advanced clinical decision support systems in future studies; see also at least ¶ [0058]: once the training set was created, it was passed to three different modeling techniques. Those techniques were logistic regression with lasso regularization (a form of generalized linear model), random forest, and gradient descent boosting. The analysis was carried out in R, with the glmnet package being the chosen implementation for the logistic regression and generalized linear model approach (hereinafter GLM) [36], the randomForest package for the random forest algorithm (hereinafter RF)[37], and xgboost or eXtreme Gradient Boosting package as the implementation of a gradient descent boosting method chosen (hereinafter XGB) [38] respectively. These techniques were selected due to their ability to select a sparse set of features while training, to avoid overfitting, and further reduce the dimensionality of the problem, where applicable. Further, GLM is commonly used in clinical practice and outcomes research, linking to similarity in related works, while RF and XGB are particularly good at dealing with data of mixed types such as these by setting differing thresholds in each particular decision tree. Further, as these last two techniques are non-linear methods, they might provide stronger results than linear methods commonly used in clinical outcomes research; see also at least ¶ [0044]: the Cohort table contained patient information, including the admission source (e.g. self-referral, transfer from another hospital, transfer from another unit, physician referral), insurance information (e.g. Medicare, private insurance, etc.), and personal information (e.g. age, gender, race if provided); see also at least ¶¶ [0046] and [0062]);
receiving, by a computer system, a true outcome of the complication (see at least ¶ [0062]: models were trained on the entire dataset as well as created by patient cohort and outcomes splits. Once trained, each algorithm generated a response for the test set. This response was a generated probability of a postoperative complication, rather than a strict label output. From this, a receiver operating characteristic curve (ROC) curve plot allowed calculation of an AUC. AUCs are often reported in clinical prediction models [1], due to the measure being unaffected by class imbalance [39]. However, to understand how such models would be used prospectively, more information should be presented regarding the predictive accuracy. After the models and AUCs were generated, an optimal threshold probability was selected to generate the classification labels. The threshold selected was that which maximized the F-score. From this classification, the true positives, true negatives, false positives, and false negatives were calculated and from that an F-score. Finally, a further metric was calculated regarding the precision of the top 20 predictions, to see if all the true positives are captured in the riskiest patients predicted as a numeric measure for how well the algorithm is calibrated. The 20 were selected based upon the total number of adverse events in each sub-group, knowing that a subset of these would exist in each fold, and to evaluate if creating a larger interval would account for all the true positives or not. This value can be altered to highest deciles of risk, quartiles, and the definitions should be created in consultation with the clinical professionals involved to understand their desires of evaluating ‘high-risk’ patients. For all the measures, the mean and 95% confidence intervals were calculated. Calibration plots were also created for the best models generated); and
updating, using a computer system, the trained machine learning model dynamically based on the true outcome of the complication to become a locally trained machine learning model configured to predict an outcome of a complication of a patient associated with the local healthcare site (see at least ¶ [0064]: the ability to interpret model predictions is highly desirable for clinicians, and to potentially help determine risk factors resulting in the prediction and potentially helping determine interventions or actions that might prevent the postoperative complication. While the models provided the selected global features, feature importance was extended to provide patient-specific results. Namely, GLM provided a vector of {right arrow over (β)}=(β1, β2, . . . ) coefficients for each parameter, which provide the global feature importance and where the length of the vector is equal to the number of features (and a large number are 0 for non-selected features).
In this arrangement, both the feature vector for each test patient, as well as the component-wise multiplication of the two vectors, are updated dynamically to become a locally trained learning model; see also at least ¶¶ [0142]: the process 400 receives (420) the continuous data collected for each patient that has been converted into time-series according to a second rule. The second rule is different than the first rule. In another example, the process 400 converts (not shown) the continuous data collected for each patient into the time-series according to the second rule; see also at least ¶ [0149]: the process 400 generates (430) a training dataset based on the third vector of data of each patient. The process 400 applies (435) a machine learning technique to the training dataset to generate a risk prediction model. The process 400 predicts a patient’s risk of postoperative complications using the risk prediction mode; see also at least ¶ [0147]).
Claim 21: Mortazavi discloses the limitations as shown in the rejections above. Further, Mortazavi, as shown, discloses the following limitations:
receiving a second medical report of a second patient at the local healthcare site (see at least ¶ [0038]: data were extracted for each admission. Each visit’s dataset consisted of data from admission time to either 24 hours or the start of patient's first procedure, whichever came first; this period of time was believed to be long enough to gather clinically relevant information on the patients to provide an understanding of patient risk prior to the procedure that resulted in the adverse event. Further, this aligned with clinical rounds typically happening every morning and procedures often happening soon after admission. The desired goal, therefore, was to create a dataset and system that would serve as a balance between early enough for appropriate decision making and late enough for considering a wide array of data; see also at least ¶ [0044]: the data were extracted from the EHR data tables shown in FIG. 1, where each VisitID in the patient cohort table had a one-to-many relationship with entries in each of the other tables of the database. The data were organized in seven tables (plus a Rothman Index Scores table), listed in Table I (see FIG. 7). These tables were joined from back-end tables storing data from the front-end of EPIC. The Cohort table contained patient information, including the admission source (e.g. self-referral, transfer from another hospital, transfer from another unit, physician referral), insurance information (e.g. Medicare, private insurance, etc.), and personal information (e.g. age, gender, race if provided). The patient population included 1025 CABG patients, 2539 PCI patients, and 1650 ICD patients. Table II (see FIG. 6) shows the event rates of respiratory failure and infection. Despite the low event rates, these patients were adversely harmed and attributed a significant cost to the hospital [13]. The data extracted were structured data organized in the back-end data warehouse for the EHR system, allowing for quick manipulation of fields for feature extraction; see also at least ¶ [0039]-[0043]; see also at least ¶ [0044]: the Cohort table contained patient information, including the admission source (e.g. self-referral, transfer from another hospital, transfer from another unit, physician referral), insurance information (e.g. Medicare, private insurance, etc.), and personal information (e.g. age, gender, race if provided));
analysing said second medical report for a second outcome of a second complication of the second patient by the locally trained machine learning model, thereby obtaining a second complication outcome (see at least ¶ [0014]: the research has led to the development of a system for identifying patients undergoing major cardiovascular procedures at risk for postoperative respiratory failure or infection, two costly outcomes as identified by at Y-NHH. The system tackles the challenges of extracting data from a production-level electronic health record provided by EPIC [33] and the tasks necessary in manipulating data for use in machine learning analytic tools. Further, after developing models to predict postoperative complications using preoperative data, the system can generate interpretable measures of risk to help identify the risk category of the patient, as well as the contributing features to risk in order to better provide clinicians with information that might help prevent such adverse events, providing a framework for more advanced clinical decision support systems in future studies; see also at least ¶ [0058]: once the training set was created, it was passed to three different modeling techniques. Those techniques were logistic regression with lasso regularization (a form of generalized linear model), random forest, and gradient descent boosting. The analysis was carried out in R, with the glmnet package being the chosen implementation for the logistic regression and generalized linear model approach (hereinafter GLM) [36], the randomForest package for the random forest algorithm (hereinafter RF)[37], and xgboost or eXtreme Gradient Boosting package as the implementation of a gradient descent boosting method chosen (hereinafter XGB) [38] respectively. These techniques were selected due to their ability to select a sparse set of features while training, to avoid overfitting, and further reduce the dimensionality of the problem, where applicable. Further, GLM is commonly used in clinical practice and outcomes research, linking to similarity in related works, while RF and XGB are particularly good at dealing with data of mixed types such as these by setting differing thresholds in each particular decision tree. Further, as these last two techniques are non-linear methods, they might provide stronger results than linear methods commonly used in clinical outcomes research; see also at least ¶ [0062]);
receiving a second true outcome of the second complication (see at least ¶ [0062]: models were trained on the entire dataset as well as created by patient cohort and outcomes splits. Once trained, each algorithm generated a response for the test set. This response was a generated probability of a postoperative complication, rather than a strict label output. From this, a receiver operating characteristic curve (ROC) curve plot allowed calculation of an AUC. AUCs are often reported in clinical prediction models [1], due to the measure being unaffected by class imbalance [39]. However, to understand how such models would be used prospectively, more information should be presented regarding the predictive accuracy. After the models and AUCs were generated, an optimal threshold probability was selected to generate the classification labels. The threshold selected was that which maximized the F-score. From this classification, the true positives, true negatives, false positives, and false negatives were calculated and from that an F-score. Finally, a further metric was calculated regarding the precision of the top 20 predictions, to see if all the true positives are captured in the riskiest patients predicted as a numeric measure for how well the algorithm is calibrated. The 20 were selected based upon the total number of adverse events in each sub-group, knowing that a subset of these would exist in each fold, and to evaluate if creating a larger interval would account for all the true positives or not. This value can be altered to highest deciles of risk, quartiles, and the definitions should be created in consultation with the clinical professionals involved to understand their desires of evaluating ‘high-risk’ patients. For all the measures, the mean and 95% confidence intervals were calculated. Calibration plots were also created for the best models generated); and
updating the locally trained machine learning model dynamically based on the second true outcome of the second complication to become a further locally trained machine learning model associated with the local healthcare site (see at least ¶ [0064]: the ability to interpret model predictions is highly desirable for clinicians, and to potentially help determine risk factors resulting in the prediction and potentially helping determine interventions or actions that might prevent the postoperative complication. While the models provided the selected global features, feature importance was extended to provide patient-specific results. Namely, GLM provided a vector of {right arrow over (β)}=(β1, β2, . . . ) coefficients for each parameter, which provide the global feature importance and where the length of the vector is equal to the number of features (and a large number are 0 for non-selected features).
In this arrangement, both the feature vector for each test patient, as well as the component-wise multiplication of the two vectors, are updated dynamically to become a locally trained learning model; see also at least ¶¶ [0142]: the process 400 receives (420) the continuous data collected for each patient that has been converted into time-series according to a second rule. The second rule is different than the first rule. In another example, the process 400 converts (not shown) the continuous data collected for each patient into the time-series according to the second rule; see also at least ¶ [0149]: the process 400 generates (430) a training dataset based on the third vector of data of each patient. The process 400 applies (435) a machine learning technique to the training dataset to generate a risk prediction model. The process 400 predicts a patient's risk of postoperative complications using the risk prediction mode; see also at least ¶ [0147]).
Claim 22: Mortazavi discloses the limitations as shown in the rejections above. Further, Mortazavi, as shown, discloses the following limitations:
wherein the trained machine learning model and the locally trained machine learning model is updated dynamically by updating before and/or during and/or after an operation for predicting the outcome or the second outcome (see at least ¶ [0064]: the ability to interpret model predictions is highly desirable for clinicians, and to potentially help determine risk factors resulting in the prediction and potentially helping determine interventions or actions that might prevent the postoperative complication. While the models provided the selected global features, feature importance was extended to provide patient-specific results. Namely, GLM provided a vector of {right arrow over (β)}=(β1, β2, . . . ) coefficients for each parameter, which provide the global feature importance and where the length of the vector is equal to the number of features (and a large number are 0 for non-selected features).
In this arrangement, both the feature vector for each test patient, as well as the component-wise multiplication of the two vectors, are updated dynamically to become a locally trained learning model; see also at least ¶¶ [0142]: the process 400 receives (420) the continuous data collected for each patient that has been converted into time-series according to a second rule. The second rule is different than the first rule. In another example, the process 400 converts (not shown) the continuous data collected for each patient into the time-series according to the second rule; see also at least ¶ [0147]).
Claim 23: Mortazavi discloses the limitations as shown in the rejections above. Further, Mortazavi, as shown, discloses the following limitations:
wherein analysing said medical report or said second medical report by the trained machine learning model provides information about whether a blood sample of the patient should be obtained (see at least ¶ [0124]: Further, along with the generated model accuracy, predictions, and calibration plots, the important features that generate the risk for a given patient were important in determining a cause and potential intervention. While each method provided a global list of important features, how each feature contributes to an individual's total risk score should be understood. Thus, the system generates an identification of which risk quartile the patient lies within, as well as the personalized response to the GLM model, as detailed in Section I-F. As an illustrative example, the GLM for the PCI respiratory failure, which achieved a mean AUC of 0.76 used the following features: Lab 1—Blood Urea Nitrogen is High −β=0.0910; see also at least ¶ [0079]).
Claim 24: Mortazavi discloses the limitations as shown in the rejections above. Further, Mortazavi, as shown, discloses the following limitations:
wherein the complication outcome is the outcome within a certain predetermined time, or wherein the second complication outcome is the second outcome within a certain predetermined time (see at least ¶ [0013]: the research focused on the extraction of all data from the time of admission to either the start of the procedure or the end of the first twenty-four hours of admission, whichever came first. This time period has been identified by Y-NHH as useful for understanding patient risk factors and determining potential interventions. The data was extracted for use in a machine learning framework to predict patient risk as well as identify the top factors for that risk. Patients and clinicians can use this risk to make better informed decisions on treatment plans with better knowledge about the risk; see also at least ¶ [0048] as vitals may have been taken multiple times between admission and procedure start time, a time-series was generated for each variable, as was for the Rothman Index. Features for the length of the time-series as well as the mean, standard deviation, minimum, and maximum were created as well. Because this created variable-length time-series, each patient's first and last readings were saved, the windowed features calculated, and additional readings were dropped, rather than determine an appropriate imputation. More complex methods might find spurious patterns in the specific readings if improperly imputed. Time-series data were represented by first reading, last reading, number of readings, mean, minimum, maximum, and standard deviation. The foregoing representations of time-series data is a non-limiting example and can include other representations like variance and the number of peaks. For laboratory readings, only the last laboratory reading was considered due to the sparse nature; see also at least ¶ [0067]).
Claim 25: Mortazavi discloses the limitations as shown in the rejections above. Further, Mortazavi, as shown, discloses the following limitations:
wherein the certain predetermined time is calculated from analysing said medical report or said second medical report or from a surgery (see at least ¶ [0013]: the research focused on the extraction of all data from the time of admission to either the start of the procedure or the end of the first twenty-four hours of admission, whichever came first. This time period has been identified by Y-NHH as useful for understanding patient risk factors and determining potential interventions. The data was extracted for use in a machine learning framework to predict patient risk as well as identify the top factors for that risk. Patients and clinicians can use this risk to make better informed decisions on treatment plans with better knowledge about the risk; see also at least ¶ [0048] as vitals may have been taken multiple times between admission and procedure start time, a time-series was generated for each variable, as was for the Rothman Index. Features for the length of the time-series as well as the mean, standard deviation, minimum, and maximum were created as well. Because this created variable-length time-series, each patient's first and last readings were saved, the windowed features calculated, and additional readings were dropped, rather than determine an appropriate imputation. More complex methods might find spurious patterns in the specific readings if improperly imputed. Time-series data were represented by first reading, last reading, number of readings, mean, minimum, maximum, and standard deviation. The foregoing representations of time-series data is a non-limiting example and can include other representations like variance and the number of peaks. For laboratory readings, only the last laboratory reading was considered due to the sparse nature; see also at least ¶ [0067]).
Claim 26: Mortazavi discloses the limitations as shown in the rejections above. Further, Mortazavi, as shown, discloses the following limitations:
wherein the complication is a sickness or a surgery (see at least ¶ [0002]: the early prediction of potential adverse events in patients has been a primary focus of outcomes research and quality improvement efforts in patient care for heart failure [1], readmissions [2], and a variety of other outcomes [3]. These efforts have focused improving patient care in a wide variety of fields, including in early detection of severe events in infants [4], respiratory complications in surgical patients [5], and blood transfusions in cardiac surgery patients [6], by understanding factors leading to conditions like costly readmissions [7], septic shock [8], and unplanned transfers to the intensive care unit [9]. These targeted models for care can help identify patient risk factors and predictors [10][11] as well as potentially address costs of care [12][13]; see also at least ¶ [0035]).
Claim 28: Mortazavi discloses the limitations as shown in the rejections above. Further, Mortazavi, as shown, discloses the following limitations:
wherein the trained machine learning model comprises a logistic regression model, entity embeddings and/or a random forest model (see at least ¶ [0058]: once the training set was created, it was passed to three different modeling techniques. Those techniques were logistic regression with lasso regularization (a form of generalized linear model), random forest, and gradient descent boosting. The analysis was carried out in R, with the glmnet package being the chosen implementation for the logistic regression and generalized linear model approach (hereinafter GLM) [36], the randomForest package for the random forest algorithm (hereinafter RF)[37], and xgboost or eXtreme Gradient Boosting package as the implementation of a gradient descent boosting method chosen (hereinafter XGB) [38] respectively. These techniques were selected due to their ability to select a sparse set of features while training, to avoid overfitting, and further reduce the dimensionality of the problem, where applicable. Further, GLM is commonly used in clinical practice and outcomes research, linking to similarity in related works, while RF and XGB are particularly good at dealing with data of mixed types such as these by setting differing thresholds in each particular decision tree. Further, as these last two techniques are non-linear methods, they might provide stronger results than linear methods commonly used in clinical outcomes research).
Claim 29: Mortazavi discloses the limitations as shown in the rejections above. Further, Mortazavi, as shown, discloses the following limitations:
wherein the medical report or the second medical report comprises pre-surgical data of the patient (see at least ¶ [0038]: data were extracted for each admission. Each visit’s dataset consisted of data from admission time to either 24 hours or the start of patient's first procedure, whichever came first; this period of time was believed to be long enough to gather clinically relevant information on the patients to provide an understanding of patient risk prior to the procedure that resulted in the adverse event. Further, this aligned with clinical rounds typically happening every morning and procedures often happening soon after admission. The desired goal, therefore, was to create a dataset and system that would serve as a balance between early enough for appropriate decision making and late enough for considering a wide array of data; see also at least ¶ [0044]: the data were extracted from the EHR data tables shown in FIG. 1, where each VisitID in the patient cohort table had a one-to-many relationship with entries in each of the other tables of the database. The data were organized in seven tables (plus a Rothman Index Scores table), listed in Table I (see FIG. 7). These tables were joined from back-end tables storing data from the front-end of EPIC. The Cohort table contained patient information, including the admission source (e.g. self-referral, transfer from another hospital, transfer from another unit, physician referral), insurance information (e.g. Medicare, private insurance, etc.), and personal information (e.g. age, gender, race if provided). The patient population included 1025 CABG patients, 2539 PCI patients, and 1650 ICD patients. Table II (see FIG. 6) shows the event rates of respiratory failure and infection. Despite the low event rates, these patients were adversely harmed and attributed a significant cost to the hospital [13]. The data extracted were structured data organized in the back-end data warehouse for the EHR system, allowing for quick manipulation of fields for feature extraction; see also at least ¶ [0039]-[0043]).
Claim 30: Mortazavi discloses the limitations as shown in the rejections above. Further, Mortazavi, as shown, discloses the following limitations:
wherein the outcome or the second outcome of the complication comprises a risk level of the complication (see at least ¶ [0024]: FIG. 4 is a flowchart of an example process for identifying patients undergoing cardiovascular procedures at risk for postoperative complications in accordance in an example embodiment of the invention; see also at least ¶ [0064]: the ability to interpret model predictions is highly desirable for clinicians, and to potentially help determine risk factors resulting in the prediction and potentially helping determine interventions or actions that might prevent the postoperative complication. While the models provided the selected global features, feature importance was extended to provide patient-specific results; see also at least ¶¶ [0016], [0062], and [0075]-[0076]).
Claim 31: Mortazavi discloses the limitations as shown in the rejections above. Further, Mortazavi, as shown, discloses the following limitations:
wherein updating the trained machine learning model is performed periodically (see at least ¶ [0064]: the ability to interpret model predictions is highly desirable for clinicians, and to potentially help determine risk factors resulting in the prediction and potentially helping determine interventions or actions that might prevent the postoperative complication. While the models provided the selected global features, feature importance was extended to provide patient-specific results. Namely, GLM provided a vector of {right arrow over (β)}=(β1, β2, . . . ) coefficients for each parameter, which provide the global feature importance and where the length of the vector is equal to the number of features (and a large number are 0 for non-selected features).
In this arrangement, both the feature vector for each test patient, as well as the component-wise multiplication of the two vectors, are updated dynamically to become a locally trained learning model; see also at least ¶¶ [0142]: the process 400 receives (420) the continuous data collected for each patient that has been converted into time-series according to a second rule. The second rule is different than the first rule. In another example, the process 400 converts (not shown) the continuous data collected for each patient into the time-series according to the second rule; see also at least ¶ [0147]).
Claim 36: Mortazavi discloses the limitations as shown in the rejections above. Further, Mortazavi, as shown, discloses the following limitations:
wherein the (further) locally trained machine learning model is a first (further) locally trained machine learning model at a first location (see at least ¶ [0044]: the data were extracted from the EHR data tables shown in FIG. 1, where each VisitID in the patient cohort table had a one-to-many relationship with entries in each of the other tables of the database. The data were organized in seven tables (plus a Rothman Index Scores table), listed in Table I (see FIG. 7). These tables were joined from back-end tables storing data from the front-end of EPIC. The Cohort table contained patient information, including the admission source (e.g. self-referral, transfer from another hospital, transfer from another unit, physician referral), insurance information (e.g. Medicare, private insurance, etc.), and personal information (e.g. age, gender, race if provided). The patient population included 1025 CABG patients, 2539 PCI patients, and 1650 ICD patients. Table II (see FIG. 6) shows the event rates of respiratory failure and infection. Despite the low event rates, these patients were adversely harmed and attributed a significant cost to the hospital [13]. The data extracted were structured data organized in the back-end data warehouse for the EHR system, allowing for quick manipulation of fields for feature extraction),
wherein the method further comprises updating the trained machine learning model at a second location different from the first location to become a second (further) locally trained machine learning model (see at least ¶ [0156]: the above described techniques can be implemented in a distributed computing system that includes a back-end component. The back-end component can, for example, be a data server, a middleware component, and/or an application server. The above described techniques can be implemented in a distributing computing system that includes a front-end component; see also at least ¶ [0157]; see also at least ¶¶ [0064], [0142], and [0147]).
Claim 37: Mortazavi discloses the limitations as shown in the rejections above. Further, Mortazavi, as shown, discloses the following limitations:
wherein first (further) locally trained machine learning model and the second (further) locally trained machine learning model are compared (see at least ¶ [0062]: models were trained on the entire dataset as well as created by patient cohort and outcomes splits. Once trained, each algorithm generated a response for the test set. This response was a generated probability of a postoperative complication, rather than a strict label output. From this, a receiver operating characteristic curve (ROC) curve plot allowed calculation of an AUC. AUCs are often reported in clinical prediction models [1], due to the measure being unaffected by class imbalance [39]. However, to understand how such models would be used prospectively, more information should be presented regarding the predictive accuracy. After the models and AUCs were generated, an optimal threshold probability was selected to generate the classification labels. The threshold selected was that which maximized the F-score. From this classification, the true positives, true negatives, false positives, and false negatives were calculated and from that an F-score. Finally, a further metric was calculated regarding the precision of the top 20 predictions, to see if all the true positives are captured in the riskiest patients predicted as a numeric measure for how well the algorithm is calibrated. The 20 were selected based upon the total number of adverse events in each sub-group, knowing that a subset of these would exist in each fold, and to evaluate if creating a larger interval would account for all the true positives or not. This value can be altered to highest deciles of risk, quartiles, and the definitions should be created in consultation with the clinical professionals involved to understand their desires of evaluating ‘high-risk’ patients. For all the measures, the mean and 95% confidence intervals were calculated. Calibration plots were also created for the best models generated; see also at least ¶ [0064]), and
wherein medical reports and true outcomes and/or second medical reports and second true outcomes of the first and second (further) locally trained machine learning models are compared for determining an optimal treatment/drug of a certain disease (see at least ¶ [0062]; see also at least ¶ [0135]: the numeric results for AUC, F-score and top 20 also aligned with calibration results. In particular, the improved AUC values indicated a better opportunity for the models to discriminate patients. With the low AUCs in CABG, all following results were similarly low, because an effective threshold delineating adverse outcomes and healthy outcomes was not clear. The lower F-scores, with the improved AUCs, were a function of the event rate. The low score indicated that the recall (sensitivity) was high but the precision was low. So while the threshold for determining clearly healthy outcomes was well-established, the mix of true positive predictions and false positive predictions is still an area for further investigation. This was also demonstrated in the top 20 precision and the calibration results. The right-skewed calibration results indicated that the adverse outcomes were mostly in the highest quartile of risk. However, with the low top 20 precision, these patients were not the highest risk. An expansion of the binary outcomes to multiple classes, with tiered understandings of the postoperative period, might be necessary to understand these false positive patients and why they are predicted differently than the large number of correctly identified true negative patients. This may also be because of other events that are not currently recorded or considered adverse outcomes in this study).
Claim 38: Mortazavi discloses the limitations as shown in the rejections above. Further, Mortazavi, as shown, discloses the following limitations:
A data processing system comprising a processor configured to perform the computer-implemented method of claim 20 (see at least ¶ [0150]: the above-described systems and methods can be implemented in digital electronic circuitry, in computer hardware, firmware, and/or software. The implementation can be as a computer program product. The implementation can, for example, be in a machine-readable storage device, for execution by, or to control the operation of, data processing apparatus. The implementation can, for example, be a programmable processor, a computer, and/or multiple computers; see also at least ¶¶ [0151]-[0159]).
Claim 39: Mortazavi discloses the limitations as shown in the rejections above. Further, Mortazavi, as shown, discloses the following limitations:
A computer program comprising instructions, which, when the program is executed by a computer, cause the computer to carry out the method of claim 20 (see at least ¶ [0150]: the above-described systems and methods can be implemented in digital electronic circuitry, in computer hardware, firmware, and/or software. The implementation can be as a computer program product. The implementation can, for example, be in a machine-readable storage device, for execution by, or to control the operation of, data processing apparatus. The implementation can, for example, be a programmable processor, a computer, and/or multiple computers; see also at least ¶¶ [0151]-[0159]).
Claim Rejections - 35 U.S.C. § 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 factual inquiries set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied for establishing a background for determining obviousness under 35 U.S.C. § 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 27 and 32-35 are rejected under AIA 35 U.S.C. § 103 as being unpatentable over Mortazavi et al. (U.S. Pub. No. 2018/0315507 A1) (hereinafter “Mortazavi”) in view of Schobel et al. (U.S. Pub. No. 2021/0327540 A1) (hereinafter “Schobel”).
Claim 27: Mortazavi discloses the limitations as shown in the rejections above.
Mortazavi does not explicitly disclose, but Schobel, as shown, teaches the following limitations:
wherein the trained machine learning model is a convolutional neural network model, and/or a long short-term neural network model (see at least ¶ [0066]: in a separate variant of a classification machine learning model, a neural network includes a plurality of layers each including one or more nodes, such as a first layer (e.g., an input layer), a second layer (e.g., an output layer), and one or more hidden layers. The neural network can include characteristics such weights and biases associated with computations that can be performed between nodes of layers. For example, a node of the input layer can receive input data, perform a computation on the input data, and output a result of the computation to a hidden layer. The hidden layer may receive outputs from one or more input layer nodes, perform a computation on the received output(s), and output a result to another hidden layer, or to the output layer. The weights and biases can affect the computations performed by each node and can be manipulated by an algorithm executing the neural network, such as an optimization algorithm being used to train the neural network to match training data. Neural networks describe a generalized approach to classification and many different variants of neural networks may be used, including, but not limited to: convolutional neural networks, deep belief networks, deep reservoir computing, restricted Boltzmann machines, deep stacking networks, tensor deep stacking networks, and/or hierarchical- deep models).
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to combine the clinical prediction techniques taught by Schobel with the prediction systems disclosed by Mortazavi, because Schobel teaches at ¶ [0114] that by considering various different machine learning models, they can be “compared to the previous models, if the model improves model fit that model is selected as the best model, if the model does not improve model fit it is discarded and the next model is tested,” which leads to discovering “the optimal model.” See M.P.E.P. § 2143(I)(G).
Moreover, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to combine the clinical prediction techniques taught by Schobel with the prediction systems disclosed by Mortazavi, because the claimed invention is merely a combination of old elements (the clinical prediction techniques taught by Schobel and the prediction systems disclosed by Mortazavi), in the combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable. See M.P.E.P. § 2143(I)(A).
Claim 32: Mortazavi discloses the limitations as shown in the rejections above.
Mortazavi does not explicitly disclose, but Schobel, as shown, teaches the following limitations:
reanalyzing the medical report for an updated outcome or the second medical report for an updated second outcome of the complication of the patient by the trained machine learning model (see at least ¶ [0079]: the clinical data for the particular subject can be used to update the machine learning engine, particularly after confirming whether or not the disease is present in the particular subject. As such, the machine learning engine adopts an iterative, self-improvement process upon deployment; see also at least ¶ [0110]: the outcome prediction system 200 can update the training data 202 based on the second values received for the second subjects, as well as the predicted pneumonia outcomes. As such, the outcome prediction system 200 can continually learn from new data regarding subjects. The outcome prediction system 200 can store the predicted pneumonia outcome with an association to the second value(s) received for the second subject in the training data 202. The predicted pneumonia outcome may be stored with an indication of being a predicted value (as compared to the known pneumonia outcomes for the plurality of first subjects), which can enable the machine learning engine 204 to process predicted outcome data stored in the training data 202 differently than known outcome data. In addition, it will be appreciated that over time, the second subject based on which a predicted outcome was generate may also have a known pneumonia outcome (e.g., based on the onset of symptoms indicating that the second subject has pneumonia, or based on an indication that the second subject does not have pneumonia, such as a sufficient period of time passing subsequent to the generation of the predicted pneumonia outcome). The outcome prediction system 200 can store the known pneumonia outcome with an association to the second value(s) received for the second subject. The outcome prediction system 200 can also store the known pneumonia outcome with an indication of an update relative to the predicted pneumonia outcome, which can enable the machine learning engine 204 to learn from the update and thus improve the variable selection and classification processes used to generate and select the candidate classification algorithm/subset of model parameters for use by the prediction engine 208. In embodiments, the outcome prediction system 200 calculates a difference between the predicted pneumonia outcome and the known pneumonia outcome, and stores this difference as the indication of the update),
wherein reanalyzing is performed after the medical report or the second medical report has been updated by an update selected from the group of: medication changes; anaesthesia data; X-ray data; lab results; vital signs; fluid input and output data; data related to insertion and removal of drains, and intravenous access; and procedural data (see at least ¶¶ [0079] and [0110]; see also at least ¶ [0049]: examples of test samples or sources of clinical parameters include, but are not limited to, biological fluids and/or tissues isolated from a subject or patient, which can be tested by the methods of the present application described herein, and include but are not limited to whole blood, peripheral blood, serum, plasma, cerebrospinal fluid, wound effluent, urine, amniotic fluid, peritoneal fluid, pleural fluid, lymph fluids, various external secretions of the respiratory, intestinal, and genitourinary tracts, tears, saliva, white blood cells, solid tumors, lymphomas, leukemias, myelomas, and combinations thereof. In particular embodiments, the sample is a serum sample, wound effluent, or a plasma sample; see also at least ¶ [0044]).
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to combine the clinical prediction techniques taught by Schobel with the prediction systems disclosed by Mortazavi, because Schobel teaches at ¶ [0110] that its techniques “improve the variable selection and classification processes used to generate and select the candidate classification algorithm/subset of model parameters.” See M.P.E.P. § 2143(I)(G).
Moreover, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to combine the clinical prediction techniques taught by Schobel with the prediction systems disclosed by Mortazavi, because the claimed invention is merely a combination of old elements (the clinical prediction techniques taught by Schobel and the prediction systems disclosed by Mortazavi), in the combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable. See M.P.E.P. § 2143(I)(A).
Claim 33: The combination of Mortazavi and Schobel teaches the limitations as shown in the rejections above. Further, Mortazavi, as shown, discloses the following limitations:
wherein the lab results are ECG data, cardiac cardiograms, blood sample data, and/or microbiological culture data (see at least ¶¶ [0087]-[0093], reciting “Lab: ECG—P Axis”; see also at least ¶ [0124], reciting “Lab 1—Blood Urea Nitrogen is High −β=0.0910”).
Claim 34: The combination of Mortazavi and Schobel teaches the limitations as shown in the rejections above. Further, Mortazavi, as shown, discloses the following limitations:
wherein the procedural data are operations, physiotherapy, and/or wound care (see at least ¶ [0018]: there are two predictive models developed using the Rothman Index as the primary feature [31][32]. Work in [31] developed a predictive model for unplanned 30-day readmissions using the Rothman Index at discharge, age, gender, insurance type, and service type (medical or surgical)).
Claim 35: The combination of Mortazavi and Schobel teaches the limitations as shown in the rejections above.
Mortazavi does not explicitly disclose, but Schobel, as shown, teaches the following limitations:
wherein reanalyzing the medical report or the second medical report is performed periodically (see at least ¶ [0131]: clinical parameters are detected, measured, assayed, assessed, and/or determined in a sample isolated from the subject at different time points, such as before, at a first time point after, and/or at a subsequent time point after the subject contracts an injury, condition, or wound that puts the subject at risk of developing pneumonia, such as a blast injury, a crush injury, a gunshot wound, or an extremity wound. For example, embodiments of the methods described herein may comprise detecting biomarkers at two, three, four, five, six, seven, eight, nine, 10 or even more time points over a period of time, such as a week or more, two weeks or more, three weeks or more, four weeks or more, a month or more, two months or more, three months or more, four months or more, five months or more, six months or more, seven months or more, eight months or more, nine months or more, ten months or more, 11 months or more, a year or more or even two years or longer. The methods also include embodiments in which the subject is assessed before and/or during and/or after treatment for pneumonia; see also at least ¶ [0110]).
The rationales to modify/combine the teachings of Mortazavi to include the teachings of Schobel are presented above regarding claim 32 and incorporated herein.
Response to Arguments
The arguments submitted with the Reply have been full considered but are not persuasive.
Applicant argues that “the claims, as a whole, are grounded in technical methods of improving machine learning models and that any judicial exceptions recited in the claims are integrated into the practical application of improving machine learning models and provide significantly more than any recited judicial exception itself.” Reply, p. 6. Examiner disagrees, because the application of the Alice test presented in the rejections leads to the opposite conclusion.
Applicant argues that the “claims recite a technical solution to improve the operation of computers and address a problem that may arise in the technical field of using machine learning models in the healthcare field, specifically, using machine learning models to predict patient outcomes.” Reply, p. 6. Applicant provides similar arguments on pages 7-8 of the Reply.
Examiner disagrees, because the improvement of these learning models (i.e., algorithms) for making medical predictions would be an improvement to the fields of medicine or medical research—not to a particular technology or technological field. In other words, the alleged improvement would be to the abstract idea, not anything relating to the technical aspects of the claimed invention. See SAP Am., Inc. v. InvestPic, LLC, No. 2017-2081, slip op. at 14 (Fed. Cir. Aug. 2, 2018) (“What is needed is an inventive concept in the non-abstract application realm. … [L]imitation of the claims to a particular field of information … does not move the claims out of the realm of abstract ideas.”). Moreover, “[A] claim for a new abstract idea is still an abstract idea.” Synopsys, Inc. v. Mentor Graphics Corp., 839 F.3d 1138, 1151 (Fed. Cir. 2016) (emphasis added). “[U]nder the Mayo/Alice framework, a claim directed to a newly discovered law of nature (or natural phenomenon or abstract idea) cannot rely on the novelty of that discovery for the inventive concept necessary for patent eligibility ….” Genetic Techs. Ltd. v. Merial L.L.C., 818 F.3d 1369, 1376 (Fed. Cir. 2016) (citations omitted). As discussed in the rejections, automating these using a computer does not change their abstract character and amounts to mere instructions to implement the identified abstract ideas on a computer.
Applicant argues that Mortazavi does not disclose locally trained machine learning model configured to predict an outcome of a complication of a patient associated with the local healthcare site because the model cited in ¶ [0064] identifies risk factors. Reply, p. 9. Examiner disagrees, because the remainder of the ¶ [0064] explains components generated from this model “are then summed together by GLM for the resulting prediction.” As Mortazavi explains at ¶ [0062] (and elsewhere), these are predictions of clinical outcomes.
Applicant argues that Mortazavi does not disclose updating the locally trained machine learning model configured to predict an outcome of a complication of a patient associated with the local healthcare site because “At no point does Mortazavi discuss using new true outcome data to update the generated prediction model.” Reply, p. 9. Examiner disagrees, because the data discussed in ¶¶ [0142], [0147], and [0149] of Mortazavi discussed augmenting previously-processed data with newer data, thereby augmenting the locally trained machine learning model.
Applicant argues that Mortazavi does not disclose trained machine learning model trained on a general cohort comprising multiple patients from multiple different healthcare sites. Reply, pp. 9-10. Examiner disagrees, because Mortazavi discloses at ¶ [0044] that patients are from “self-referral, transfer from another hospital, transfer from another unit, physician referral”—i.e., from multiple different healthcare sites—and at ¶ [0136] that the data includes “categorical data and continuous data collected from patients”—i.e., multiple patients.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
The prior art made of record and not relied upon is considered pertinent to applicant’s disclosure. The following references have been cited to further show the state of the art with respect to predicting medical outcomes.
Bihorac et al. (U.S. Pub. No. 2020/0161000 A1) (prediction of complications after surgery);
Merath et al. (“Use of machine learning for prediction of patient risk of postoperative complications after liver, pancreatic, and colorectal surgery.” Journal of Gastrointestinal Surgery 24.8 (2020): 1843-1851).
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Christopher Tokarczyk, whose telephone number is 571-272-9594. The examiner can normally be reached Monday-Thursday between 6:00 AM and 4:00 PM Eastern.
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, Mamon Obeid, can be reached at 571-270-1813. 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.
/CHRISTOPHER B TOKARCZYK/ Primary Examiner, Art Unit 3687
Prosecution Insights