DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Status of the Claims
The status of the claims as of the response filed 7/20/2026 is as follows: Claims 2, 4, 11, and 19 are cancelled, and all previously given rejections for these claims are considered moot. Claims 1, 13, and 22 are currently amended. Claims 3, 8-9, 20-21, and 23 are as previously presented. Claims 5-7, 10, 12, and 14-18 are original. Claims 1, 3, 5-10, 12-18, and 20-23 are currently pending in the application and have been considered below.
Response to Amendment
Rejection Under 35 USC 112(b)
Claims 1, 13, and 22 have been sufficiently amended to correct the indefinite language identified in the previous office action such that the corresponding 35 USC 112(b) rejections are withdrawn.
Rejection Under 35 USC 101
The claims have been amended to include administration of a particular treatment (intravenous antibiotics and optionally draining infected synovial fluid) to treat patients identified as having above a threshold probability of having a specific condition (periprosthetic joint infection). Accordingly, the recited abstract idea is integrated into a practical application by providing a particular treatment for a medical condition in manner similar to the eligible examples outlined in MPEP 2106.04(d)(2). Accordingly, the corresponding 35 USC 101 rejections are withdrawn.
Rejection Under 35 USC 103
The amendments made to the claims introduce limitations that are not fully addressed in the previous office action, and thus the corresponding 35 USC 103 rejections are withdrawn. However, Examiner will consider the amended claims in light of an updated prior art search and address their patentability with respect to prior art below.
Response to Arguments
Rejection Under 35 USC 103
On pages 9-10 of the response filed 7/20/2026 Applicant argues that the combination of Schobel and Sheng does not teach or suggest use of alpha defensin and at least one of leukocyte esterase, calprotectin, neutrophile elastase, lipocalcin, and d-dimer as predictor variables for PJI as in amended claim 1. Applicant’s arguments are fully considered, but are not persuasive. Although Examiner agrees that Schobel and Sheng fail to explicitly disclose that the clinical parameters of the outcome prediction model include these specific biomarkers, Sheng does disclose measures of alpha defensin, leukocyte esterase, and d-dimer being utilized as part of existing, known methods of diagnosing PJI (Sheng Pg 2). It therefore would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to utilize alpha defensin and at least one of leukocyte esterase and d-dimer as clinical parameters for training and execution of the model in order to utilize biomarkers known to be associated with and useful for diagnosis of a PJI outcome (as suggested by Sheng Pg 2), thereby improving the diagnostic accuracy of the model. Accordingly, Examiner submits that the presently cited prior art references do teach the limitation at issue, as explained in the updated 35 USC 103 rejections below.
Claim Interpretation
Note: claims 1 and 13 each include the optional limitation “optionally draining infected synovial fluid from an affected joint of the subject.” Per MPEP 2111.04(I): “Claim scope is note limited by claim language that suggests or makes optional but does not require steps to be performed, or by claim language that does not limit a claim to a particular structure.” Accordingly, the optional limitation cited above need not be taught by the prior art under the broadest reasonable interpretation of the claim. However, in the interest of compact prosecution, this limitation is addressed with prior art below.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claim 9 is rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 9 recites “G) determining the threshold value.” However, parent claim 1 introduces a threshold value in step E), and parent claim 8 also introduces “a threshold value” in line 2. It is unclear which threshold is being referenced by “the threshold value” of claim 9, because “the threshold value” could be referring to the threshold value of claim 1 or the threshold value of claim 8, which may or may not be different threshold values, rendering claim 9 indefinite. For purposes of examination, Examiner will consider each of the threshold values of claims 1, 8, and 9 to be the same threshold value.
The following is a quotation of 35 U.S.C. 112(d):
(d) REFERENCE IN DEPENDENT FORMS.—Subject to subsection (e), a claim in dependent form shall contain a reference to a claim previously set forth and then specify a further limitation of the subject matter claimed. A claim in dependent form shall be construed to incorporate by reference all the limitations of the claim to which it refers.
The following is a quotation of pre-AIA 35 U.S.C. 112, fourth paragraph:
Subject to the following paragraph [i.e., the fifth paragraph of pre-AIA 35 U.S.C. 112], a claim in dependent form shall contain a reference to a claim previously set forth and then specify a further limitation of the subject matter claimed. A claim in dependent form shall be construed to incorporate by reference all the limitations of the claim to which it refers.
Claims 3 and 14 are rejected under 35 U.S.C. 112(d) or pre-AIA 35 U.S.C. 112, 4th paragraph, as being of improper dependent form for failing to further limit the subject matter of the claim upon which it depends, or for failing to include all the limitations of the claim upon which it depends.
Claims 3 and 14 each recite “wherein treating the periprosthetic joint infection comprises treating the subject with an antibiotic.” However, limitation F) of parent claims 1 and 13 already specify “treating the periprosthetic joint infection in the subject by administering intravenous antibiotics to the subject.” Because the parent claims already recite treating the PJI by treating the subject with an antibiotic, claims 3 and 14 do not further limit the subject matter of the claims upon which they respectively depend, instead merely restating a portion of limitation F). Applicant may cancel the claim(s), amend the claim(s) to place the claim(s) in proper dependent form, rewrite the claim(s) in independent form, or present a sufficient showing that the dependent claim(s) complies with the statutory requirements.
Claim Rejections - 35 USC § 103
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1, 3, 5-10, 12-18, and 20-23 are rejected under 35 U.S.C. 103 as being unpatentable over Schobel et al. (US 20210327540 A1) in view of Sheng et al. (CN 115954102 A) and Luhmann (US 20220187314 A1).
Claim 1
Schobel teaches a method comprising steps of:
A) obtaining plural pieces of training data from a plurality of subjects, each piece of training data being an indicator of a (Schobel [0008], [0065], [0089], noting training data from multiple subjects is obtained that represents the relationships of input clinical parameters to known clinical outcome data (i.e. data from confirmed cases of a given outcome); see also [0030], noting the clinical outcomes can include any disease or condition that a subject can be diagnosed to have, including infections like pneumonia or sepsis);
B) using the plural pieces of training data to pre-train a machine learning model, wherein the machine learning model learns patterns and relationships between the plural pieces of training data, and wherein the machine learning model assigns different weights to various indicators based on their predictive power rather than treating all indicators equally (Schobel [0009], [0065]-[0066], [0070], noting the training data is used to train various types of machine learning models to learn relationships between the values of each input variable and the corresponding outcomes, including variables with different predictive powers towards an outcome as in [0044]; the various types of trained models utilize different mathematical functions to model the different influences of each input variable, considered equivalent to assigning different weights to various indicators based on their predictive power such as via weights between nodes in a neural network as in [0066], via a learned mathematical regression function (i.e. with corresponding weight/coefficients) in a regression model as in [0070], via calculated relationships (i.e. weights) between values of each variable in a Naïve Bayes algorithm as in [0065], via individual weight value assigned to values in a risk profile as in [0137]-[0139], etc.);
C) wherein the plural pieces of training data of B) correspond to a combination of data that is associated with (Schobel [0065], noting the training data represents relationships of input clinical parameters to clinical outcomes, including parameters that are highly correlated with or predictive of the presence of the outcome);
D) feeding plural pieces of data obtained from a subject to the machine learning model (Schobel [0079], [0105], [0117], noting new clinical parameters for a subject are obtained and applied to the trained model to predict the outcome);
E) determining the likelihood of the subject having a (Schobel [0038], [0079], [0117], [0139], noting the trained model is used to predict the outcome, including whether the subject is likely or high risk to have one or more clinical outcomes; Examiner notes that determining whether the subject is likely to have the clinical outcome via comparison to a threshold as in [0117] & [0139] is a common method of transforming a continuous probability output to a binary determination such that the reference clearly contemplates that the output may comprise a continuous probability score prior to being binarized by the threshold); and
F) when the continuous probability score exceeds the threshold value, treating the (Schobel [0007], noting patients determined to have an increased risk of the clinical outcome (e.g. infection as in [0030]) may be treated, e.g. via initiation of antibiotic therapy; patients may be determined to have an increased risk of a given clinical outcome when the continuous probability score exceeds a threshold value as in [0117] & [0139] such that the initiation of antibiotic treatment is considered to be responsive to the score exceeding the threshold value),
wherein, the plurality of data of A) and D) includes percentage, a test measuring c-reactive protein concentration, a test measuring alpha defensin concentration, a test to detect presence of microbial antigen, a test measuring calprotectin, a test measuring neutrophil elastase, a test measuring leukocyte esterase, a test measuring lipocalcin, a test measuring monocyte-to-lymphocyte ratio, a test measuring neutrophil-to-lymphocyte ratio, a test measuring platelet-to-lymphocyte ratio, a test measuring absolute neutrophil count, a test measuring d-dimer, a test measuring erythrocyte sedimentation rate, a test measuring lactate or L-lactate, the affected joint, a subject’s age, and a subject’s gender (Schobel [0043], noting one or more (i.e. at least two) of the clinical parameters may include age and gender).
In summary, Schobel teaches a method for training and using a machine learning model to predict and initiate treatment (e.g. antibiotics) for a variety of clinical outcomes, including risk or presence of infections like pneumonia or sepsis. Schobel further contemplates the outcome prediction being performed for any type of test subject, including those who have “an injury, condition, or wound that puts the subject at risk of developing one or more clinical outcomes, such as having a viral or bacterial infection,… undergoing a medical surgical or dental procedure, having an open wound or trauma,… having undergone medical interventions such as central line placement or intubation,… undergoing organ transplant procedure” and others (see [0037]). However, Schobel fails to explicitly disclose that the predicted and treated infection outcome is a periprosthetic joint infection outcome, that the treatment includes intravenous antibiotics and optionally draining infected synovial fluid from an affected joint of the subject, and that the plurality of data of steps A) and D) includes alpha defensin and at least one of a test measuring leukocyte esterase, a test measuring calprotectin, a test measuring neutrophile elastase, a test measuring lipocalcin, and a test measuring d-dimer.
However, Sheng teaches an analogous method of training and using a clinical predictive machine learning model that is specialized for predicting the outcome of periprosthetic joint infection (which may arise when a patient undergoes a surgical procedure like artificial joint replacement per Sheng Pg 2) based on a variety of clinical indicators associated with PJI (Sheng Pg 4, noting at least 46 index clinical parameters may be considered as inputs to the PJI model, including age, joint type, gender, neutrophil percentage, blood sedimentation value, c-reactive protein value, etc.) for the purpose of guiding treatment of the patient (Sheng abstract). It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the predicted and treated infection outcome for patients who have recently undergone a relevant surgical procedure as in Schobel to specifically include PJI as in Sheng in order to improve the precision of PJI diagnosis and treatment, which is a known type of infectious risk for patients who have undergone specific surgical procedures and currently lacks a specific diagnostic index and would result in reduced misdiagnosis and mistreatment of PJI which is a dangerous and clinically significant clinical outcome (as suggested by Sheng Pgs 1-2).
Further, though Sheng fails to explicitly disclose that the clinical parameters of the model include alpha defensin and at least one of a test measuring leukocyte esterase, a test measuring calprotectin, a test measuring neutrophile elastase, a test measuring lipocalcin, and a test measuring d-dimer, it does disclose measures of alpha defensin, leukocyte esterase, and d-dimer being utilized as part of existing, known methods of diagnosing PJI (Sheng Pg 2). It therefore would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to utilize alpha defensin and at least one of leukocyte esterase and d-dimer as clinical parameters for training and execution of the diagnostic model in order to utilize biomarkers known to be associated with and useful for diagnosis of a PJI outcome (as suggested by Sheng Pg 2), thereby improving the diagnostic accuracy of the model.
Though the present combination teaches the administration of antibiotics to a patient identified as being at high risk for a certain condition (e.g. PJI), it fails to explicitly disclose that the antibiotics are administered intravenously, nor the optional draining of infected synovial fluid from an affected joint of the subject. However, Luhmann teaches that treatments for patients diagnosed with a joint infection such as septic arthritis include intravenous antibiotics (Luhmann [0005], [0070], [0077], [0109], [0114]) and drainage of the infected site (Luhmann [0071], [0109], [0114]). It therefore would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the treatment administered to a patient identified as being at high risk for a PJI as in the combination to include intravenous antibiotics and optional drainage of the infected joint as in Luhmann in order to quickly administer appropriate treatments known to be ideal against joint infections (as suggested by Luhmann [0005] & [0070]-[0071]), thereby improving patient care.
Claim 13
Schobel teaches a method comprising steps of:
A) obtaining plural pieces of training data from a plurality of subjects each piece of training data being an indicator of a (Schobel [0008], [0065], [0089], noting training data from multiple subjects is obtained that represents the relationships of input clinical parameters to known clinical outcome data (i.e. data from confirmed cases of a given outcome); see also [0030], noting the clinical outcomes can include any disease or condition that a subject can be diagnosed to have, including infections like pneumonia or sepsis);
B) using the plural pieces of training data to pre-train a machine learning model, wherein the machine learning model learns patterns and relationships between the plural pieces of training data, and wherein the machine learning model assigns different weights to various indicators based on their predictive power rather than treating all indicators equally (Schobel [0009], [0065]-[0066], [0070], noting the training data is used to train various types of machine learning models to learn relationships between the values of each input variable and the corresponding outcomes, including variables with different predictive powers towards an outcome as in [0044]; the various types of trained models utilize different mathematical functions to model the different influences of each input variable, considered equivalent to assigning different weights to various indicators based on their predictive power such as via weights between nodes in a neural network as in [0066], via a learned mathematical regression function (i.e. with corresponding weight/coefficients) in a regression model as in [0070], via calculated relationships (i.e. weights) between values of each variable in a Naïve Bayes algorithm as in [0065], via individual weight value assigned to values in a risk profile as in [0137]-[0139], etc.);
C) wherein the plural pieces of training data of B) correspond to a combination of data that is associated with (Schobel [0065], noting the training data represents relationships of input clinical parameters to clinical outcomes, including parameters that are highly correlated with or predictive of the presence of the outcome);
D) feeding plural pieces of data obtained from a subject to the machine learning model (Schobel [0079], [0105], [0117], noting new clinical parameters for a subject are obtained and applied to the trained model to predict the outcome);
E) determining the likelihood of a subject having a (Schobel [0038], [0079], [0117], [0139], noting the trained model is used to predict the outcome, including whether the subject is likely or high risk to have one or more clinical outcomes; Examiner notes that determining whether the subject is likely to have the clinical outcome via comparison to a threshold as in [0117] & [0139] is a common method of transforming a continuous probability output to a binary determination such that the reference clearly contemplates that the output may comprise a continuous probability score prior to being binarized by the threshold); and
F) when the continuous probability score exceeds a threshold value, treating the (Schobel [0007], noting the clinical outcome (e.g. infection as in [0030]) may be treated, e.g. via initiation of antibiotic therapy; patients may be determined to have an increased risk of a given clinical outcome when the outcome score exceeds a threshold value as in [0117] & [0139] such that the initiation of antibiotic treatment is considered to be responsive to the continuous probability score exceeding a threshold value),
wherein the output of the machine learning model is compared against the threshold value, the output of the machine learning model is delivered as a probability score, the output of the machine learning model is delivered as a rank-percentile, the output of the machine learning model is delivered as a confidence score, the output of the machine learning model is delivered as a categorical range, or a combination thereof (Schobel [0117], [0139], noting the predicted outcome can include whether the subject is likely or high risk to have one or more clinical outcomes as compared to a threshold).
In summary, Schobel teaches a method for training and using a machine learning model to predict and initiate treatment (e.g. antibiotics) for a variety of clinical outcomes, including risk or presence of infections like pneumonia or sepsis. Schobel further contemplates the outcome prediction being performed for any type of test subject, including those who have “an injury, condition, or wound that puts the subject at risk of developing one or more clinical outcomes, such as having a viral or bacterial infection,… undergoing a medical surgical or dental procedure, having an open wound or trauma,… having undergone medical interventions such as central line placement or intubation,… undergoing organ transplant procedure” and others (see [0037]). However, Schobel fails to explicitly disclose that the predicted and treated infection outcome is a periprosthetic joint infection outcome, or that the treatment includes intravenous antibiotics and optionally draining infected synovial fluid from an affected joint of the subject.
However, Sheng teaches an analogous method of training and using a clinical predictive machine learning model that is specialized for predicting the outcome of periprosthetic joint infection (which may arise when a patient undergoes a surgical procedure like artificial joint replacement per Sheng Pg 2) based on a variety of clinical indicators associated with PJI (Sheng Pg 4, noting at least 46 index clinical parameters may be considered as inputs to the PJI model, including age, joint type, gender, neutrophil percentage, blood sedimentation value, c-reactive protein value, etc.) for the purpose of guiding treatment of the patient (Sheng abstract). It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the predicted and treated infection outcome for patients who have recently undergone a relevant surgical procedure as in Schobel to specifically include PJI as in Sheng in order to improve the precision of PJI diagnosis and treatment, which is a known type of infectious risk for patients who have undergone specific surgical procedures and currently lacks a specific diagnostic index and would result in reduced misdiagnosis and mistreatment of PJI which is a dangerous and clinically significant clinical outcome (as suggested by Sheng Pgs 1-2).
Though the present combination teaches the administration of antibiotics to a patient identified as being at high risk for a certain condition (e.g. PJI), it fails to explicitly disclose that the antibiotics are administered intravenously, nor the optional draining of infected synovial fluid from an affected joint of the subject. However, Luhmann teaches that treatments for patients diagnosed with a joint infection such as septic arthritis include intravenous antibiotics (Luhmann [0005], [0070], [0077], [0109], [0114]) and drainage of the infected site (Luhmann [0071], [0109], [0114]). It therefore would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the treatment administered to a patient identified as being at high risk for a PJI as in the combination to include intravenous antibiotics and optional drainage of the infected joint as in Luhmann in order to quickly administer appropriate treatments known to be ideal against joint infections (as suggested by Luhmann [0005] & [0070]-[0071]), thereby improving patient care.
Claims 3 and 14
Schobel in view of Sheng and Luhmann teaches the method of claim 1, and the combination further teaches wherein treating the periprosthetic joint infection comprises treating the subject with an antibiotic (Schobel [0007], noting the clinical outcome (e.g. PJI when considered in the context of the combination with Sheng) may be treated via initiation of antibiotic therapy).
Claim 14 recites substantially similar subject matter as claim 3, and is also rejected as above.
Claims 5 and 16
Schobel in view of Sheng and Lumann teaches the method of claim 1, and the combination further teaches wherein the plurality of data comprises a panel of information that is fed into the machine learning model (Schobel [0043], [0134], noting one or more clinical parameters may be input to the machine learning model, considered to include a “panel” of information when at least two parameters are present).
Claim 16 recites substantially similar subject matter as claim 5, and is also rejected as above.
Claims 6 and 17
Schobel in view of Sheng and Lumann teaches the method of claim 1, and the combination further teaches wherein the machine learning model comprises at least one of a logistic regression model, a support vector machine model, a decision trees model, a random forests model, an adaptive boosting trees model, a gradient boosting trees model, an explainable boosting machine model, a nearest neighbors model, a neural networks model, a KMeans model, a gaussian mixture model, a hierarchical clustering model, a density-based spatial clustering of applications with noise (DBSCAN) model, a fuzzy clustering model, a principal component analysis (PCA) model, a linear discriminant analysis (LDA) model, a factor analysis of mixed data or factorial analysis of mixed data (FAMD) model, a single value decomposition (SVD) model, and a t-distributed stochastic neighbor embedding (t-SNE) model (Schobel [0012], [0064], noting a variety of machine learning model types that may be used for classification, including logistic regression, support vector machine, decision trees, random forest, etc.).
Claim 17 recites substantially similar subject matter as claim 6, and is also rejected as above.
Claims 7 and 18
Schobel in view of Sheng and Lumann teaches the method of claim 1, and the combination further teaches wherein the machine learning model is a first machine learning model and the method further comprises subjecting the plurality of data to a second machine learning model that is different from the first machine learning model (Schobel [0072], noting many implementations of the method include use of multiple related models that are different by virtue of being trained at different times, on different datasets, and/or of different model types. See also [0062], noting a separate phase of training the models can involve variable selection via applying the training data to supervised machine learning algorithms different from those generated in the classification stage).
Claim 18 recites substantially similar subject matter as claim 7, and is also rejected as above.
Claim 8
Schobel in view of Sheng and Lumann teaches the method of claim 1, and the combination further teaches wherein the output of the machine learning model is compared against a threshold value, the output of the machine learning model is delivered as a probability score, the output of the machine learning model is delivered as a rank-percentile, the output of the machine learning model is delivered as a confidence score, the output of the machine learning model is delivered as a categorical range, or a combination thereof (Schobel [0117], [0139], noting the predicted outcome can include whether the subject is likely or high risk to have one or more clinical outcomes as compared to a confidence threshold).
Claim 19 recites substantially similar subject matter as claim 8, and is also rejected as above.
Claims 9 and 20
Schobel in view of Sheng and Lumann teaches the method of claim 8, and the combination further teaches G) determining the threshold value (Schobel [0139], noting the threshold value may be set (i.e. determined) by a combined risk index from a population of control/normal subjects).
Claim 20 recites substantially similar subject matter as claim 9, and is also rejected as above.
Claim 10
Schobel in view of Sheng and Lumann teaches the method of claim 1, and the combination further teaches wherein the plural pieces of data are obtained by one or more health care providers (Schobel [0043], noting a variety of clinical parameters that would be obtained by a health care provider, including blood test measurements and clinically-calculated indices/scores).
Claim 11
Schobel in view of Sheng and Lumann teaches the method of claim 1, and the combination further teaches wherein the plural pieces of data at A) is obtained from multiple subjects (Schobel [0008], noting the training database includes data associated with a plurality of subjects).
Claim 12
Note: the previous testing status of the subject being evaluated has no functional impact on the operations and steps recited in the method, and instead represents a description of an intended use case population. That is, the functional steps of the method would be performed identically regardless of whether the subject had or had not been previously tested for a PJI and received an inconclusive or any other type of result, such that this limitation is not patentably limiting. However, in the interest of compact prosecution, this limitation is addressed with art below.
Schobel in view of Sheng and Lumann teaches the method of claim 1, and the combination further teaches wherein the subject had been previously tested for a periprosthetic joint infection and received an inconclusive result (Schobel [0131], [0141], noting the clinical parameters are detected and utilized for prediction at multiple points in time, indicating that a given subject may have been previously evaluated for risk of the clinical outcome (i.e. PJI in the context of the combination) and found to have any type of result, including an inconclusive result such as a slightly increased risk relative to a reference population as in [0038]).
Claim 15
Schobel in view of Sheng and Lumann teaches the method of claim 13, and the combination further teaches wherein, the plurality of data of A) and D) includes at least two of a test measuring protein concentration and/or total protein content, a test measuring red blood cell concentration, a test measuring white blood cell concentration, a neutrophil or polymorphonuclear cell percentage, a test measuring c-reactive protein concentration, a test measuring alpha defensin concentration, a test to detect presence of microbial antigen, a test measuring calprotectin, a test measuring neutrophil elastase, a test measuring leukocyte esterase, a test measuring lipocalcin, a test measuring monocyte-to-lymphocyte ratio, a test measuring neutrophil-to-lymphocyte ratio, a test measuring platelet-to-lymphocyte ratio, a test measuring absolute neutrophil count, a test measuring d-dimer, a test measuring erythrocyte sedimentation rate, a test measuring lactate or L-lactate, the affected joint, a subject’s age, and a subject’s gender (Schobel [0043], noting one or more (i.e. at least two) of the clinical parameters may include age and gender. See also Sheng Pg 4, noting at least 46 index clinical parameters may be considered as inputs to the PJI model, including age, joint type, gender, neutrophil percentage, blood sedimentation value, c-reactive protein value, etc.).
Claim 21
Schobel in view of Sheng and Lumann teaches the method of claim 1, and the combination further teaches wherein the machine learning model is configured to provide a diagnosis allowing for diagnosis even when certain test results are unavailable (Schobel [0106], [0117], noting the clinical outcome (i.e. diagnosis) can be predicted even when there is missing data in the inputs, e.g. via performing imputation).
Claim 22
Schobel in view of Sheng and Lumann teaches the method of claim 1, and the combination further teaches wherein step B) comprises training the machine learning model on datasets of historical patient information including both confirmed cases of periprosthetic joint infection and non-infected controls (Schobel [0008], [0056], [0061]-[0065], noting the models may be trained via supervised learning data including outcomes of a plurality of subjects (e.g. whether a particular clinical outcome is present or not as in [0065], which would include PJI when considered in the context of the combination with Sheng); the presence of recorded yes/no outcomes indicates that the training data is historical patient information because the outcomes are already known such that diagnosis has happened in the past. See also [0139] & [0146], noting further inclusion of population data of normal patients that do not have the clinical outcome of interest).
Claim 23
Schobel in view of Sheng and Lumann teaches the method of claim 1, and the combination further teaches wherein the machine learning model comprises an ensemble of multiple classifiers (Schobel [0067]-[0069], noting the trained model can include a random forest that combines the outputs of multiple decision tree models, i.e. an ensemble model).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Kuiper et al. (Reference U on the accompanying PTO-892) describes existing treatments for PJI, including intravenous antibiotics and irrigation/drainage of the infected site.
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.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to KAREN A HRANEK whose telephone number is (571)272-1679. The examiner can normally be reached M-F 8:00-4:00 ET.
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, Shahid Merchant can be reached at 571-270-1360. 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.
/KAREN A HRANEK/ Primary Examiner, Art Unit 3684
Prosecution Insights