DETAILED ACTION
Notice of AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Information Disclosure Statement
The information disclosure statement submitted on 5/31/2024 has been considered.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Regarding Step 1 of the Alice/Mayo framework, Claims 1-10 are directed to a method (a process), Claims 11-17 are directed to a system (a machine), and Claims 18-20 are directed to a non-transitory computer readable medium (an article of manufacture), which each fall within one of the four statutory categories of inventions.
Regarding Claim 1
Step 2A, prong 1 (Is the claim directed to a law of nature, a natural phenomenon or an abstract idea).
Claim 1 recites the following mental processes, that in each case under the broadest reasonable interpretation, covers performance of the limitation in the mind (including an observation, evaluation, judgment, opinion) or with the aid of pencil and paper but for the recitation of generic computer components (e.g., “computer-implemented”, “processors”, “machine-learning model”).
deriving, ... one or more features from the historical data (under the broadest reasonable interpretation, a human can mentally derive features from reviewing historical data, such as identifying a particular blood test as being particularly indicative of a particular condition)
determining, ... a condition of the target entity ..., (under the broadest reasonable interpretation, a human such as a medical physician can determine the condition of a patient entity)
determining a specific condition associated with each entity of the plurality of entities based on the plurality of datasets; (under the broadest reasonable interpretation, a human such as a medical physician can review medical information for several patients and determine specific medical diagnoses for each patient)
generating an identifier for each entity of the plurality of entities based on the determined specific condition; (under the broadest reasonable interpretation, a human can mentally generate such an identifier, such as using the identifier “CC” for patients diagnosed with colon cancer)
deriving one or more training features for each entity of the plurality of entities from historical training data associated with the entity; and (under the broadest reasonable interpretation, a human can mentally derive features from reviewing historical data about several patients, such as identifying a particular blood test as being particularly indicative of a particular condition)
Step 2A, prong 2 (Does the claim recite additional elements that integrate the judicial exception into a practical application?).
The judicial exception is not integrated into a practical application.
Regarding the “receiving, by one or more processors, historical data associated with a target entity from a plurality of data sources” limitation, such additional element of a data gathering step is recited at a high level of generality and amounts to extra-solution activity of receiving data, i.e. pre-solution activity of gathering data for use in the claimed process (see MPEP 2106.05(g)). Regarding the “ ...by the one or more processors...” limitation, such limitation is recited at a high-level of generality and amounts to no more than adding the words “apply it” (or an equivalent) with the judicial exception. In particular, the claim only recites the additional element of a processor. This additional element is recited at a high-level of generality and amounts to no more than mere instructions to apply the exception using a generic computer component (a processor). Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea (See MPEP 2106.05(f)).
Regarding the “by applying the one or more features to a machine-learning model” limitation, such limitation is recited at a high-level of generality and amounts to no more than adding the words “apply it” (or an equivalent) with the judicial exception. In particular, the claim only recites the additional element of a generic machine learning model. This additional element is recited at a high-level of generality and amounts to no more than mere instructions to apply the exception using a generic computer component (generic machine learning model). Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea (See MPEP 2106.05(f)).
Regarding the “wherein the machine-learning model has been trained by” limitation, such limitation is recited at a high-level of generality and amounts to no more than adding the words “apply it” (or an equivalent) with the judicial exception. In particular, the claim only recites the additional element of training a generic machine learning model. This additional element is recited at a high-level of generality and amounts to no more than mere instructions to apply the exception using a generic computer component (training a generic machine learning model). Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea (See MPEP 2106.05(f)).
Regarding the “receiving a plurality of datasets associated with each entity of a plurality of entities” limitation, such additional element of a data gathering step is recited at a high level of generality and amounts to extra-solution activity of receiving data, i.e. pre-solution activity of gathering data for use in the claimed process (see MPEP 2106.05(g)).
Regarding the “inputting the identifier and the one or more training features for each entity to the machine-learning model to learn associations between the identifiers and the training features associated with the plurality of entities” limitation, such limitation is recited at a high-level of generality and amounts to no more than adding the words “apply it” (or an equivalent) with the judicial exception. In particular, the claim only recites the additional element of using a generic machine learning model. This additional element is recited at a high-level of generality and amounts to no more than mere instructions to apply the exception using a generic computer component (using a generic machine learning model). Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea (See MPEP 2106.05(f)).
Accordingly, at Step 2A, prong two, after considering all claim elements individually and as an ordered combination, it is determined that the claims do not integrate the judicial exception into a practical application.
Step 2B (Does the claim recite additional elements that amount to significantly more than the judicial exception?)
In accordance with Step 2B, the claim does not include additional elements that are sufficient to amount to significantly more that the judicial exception.
Regarding the “receiving, by one or more processors, historical data associated with a target entity from a plurality of data sources” limitation, as discussed above, the additional element of a data gathering step is recited at a high level of generality and amounts to extra-solution activity of receiving data, i.e. pre-solution activity of gathering data for use in the claimed process. The courts have found limitations directed to obtaining information electronically, recited at a high level of generality, to be well-understood, routine, and conventional (see MPEP 2106.05(d)(II), “receiving or transmitting data over a network”, "electronic record keeping," and "storing and retrieving information in memory"). Regarding the “ ...by the one or more processors...” limitation, such limitation is recited at a high-level of generality and amounts to no more than adding the words “apply it” (or an equivalent) with the judicial exception, because the limitation merely provides instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea. Accordingly, this additional element does not add significantly more than the judicial exception. (See MPEP 2106.05(f)).
Regarding the “by applying the one or more features to a machine-learning model” limitation, such limitation is recited at a high-level of generality and amounts to no more than adding the words “apply it” (or an equivalent) with the judicial exception, because the limitation merely provides instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea. Accordingly, this additional element does not add significantly more than the judicial exception. (See MPEP 2106.05(f)).
Regarding the “wherein the machine-learning model has been trained by” limitation, such limitation is recited at a high-level of generality and amounts to no more than adding the words “apply it” (or an equivalent) with the judicial exception, because the limitation merely provides instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea. Accordingly, this additional element does not add significantly more than the judicial exception. (See MPEP 2106.05(f)).
Regarding the “receiving a plurality of datasets associated with each entity of a plurality of entities” limitation, as discussed above, the additional element of a data gathering step is recited at a high level of generality and amounts to extra-solution activity of receiving data, i.e. pre-solution activity of gathering data for use in the claimed process. The courts have found limitations directed to obtaining information electronically, recited at a high level of generality, to be well-understood, routine, and conventional (see MPEP 2106.05(d)(II), “receiving or transmitting data over a network”, "electronic record keeping," and "storing and retrieving information in memory").
Regarding the “inputting the identifier and the one or more training features for each entity to the machine-learning model to learn associations between the identifiers and the training features associated with the plurality of entities” limitation, such limitation is recited at a high-level of generality and amounts to no more than adding the words “apply it” (or an equivalent) with the judicial exception, because the limitation merely provides instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea. Accordingly, this additional element does not add significantly more than the judicial exception. (See MPEP 2106.05(f)).
Accordingly, at Step 2B after considering all claim elements individually and as an ordered combination, it is determined that the claims do not integrate the judicial exception into a practical application.
Regarding Claim 2
Step 2A, Prong 1
wherein the condition determined for the target entity indicates whether or not the target entity has an undocumented condition or a delayed documented condition. (under the broadest reasonable interpretation, a human can mentally determine if the patient has an undiagnosed condition (such as a medical physician making an initial diagnosis) or determining that the patient’s diagnosis has come too late for treatment to be effective)
Regarding Step 2A, Prong 2, the claim does not include any additional elements that integrate the judicial exception into a practical application and regarding Step 2B, there are no additional elements recited that amount to significantly more than the judicial exception.
Regarding Claim 3
Step 2A, Prong 1
wherein the specific condition determined for each entity is one of: an undocumented condition, a delayed documented condition, or a non-condition. (under the broadest reasonable interpretation, a human such as a medical physician can mentally determine if the condition, for each entity, is undocumented (e.g., previously not diagnosed), a delayed documented condition (e.g., diagnosis is too late for treatment to be effective), or a non-condition (the user does not have the condition))
Regarding Step 2A, Prong 2, the claim does not include any additional elements that integrate the judicial exception into a practical application and regarding Step 2B, there are no additional elements recited that amount to significantly more than the judicial exception.
Regarding Claim 4
Step 2A, Prong 2
Regarding the “wherein the plurality of datasets associated with each entity include one or more of: a claims dataset; a lab dataset and/or a pharmacy dataset; or a complications dataset” limitation, such additional element of a data gathering step is recited at a high level of generality and amounts to extra-solution activity of receiving data, i.e. pre-solution activity of gathering data for use in the claimed process (see MPEP 2106.05(g)). Moreover, this just related to particular types of information stored in databases, and therefore such limitation amounts to no more than generally linking the use of a judicial exception to a particular technological environment or field of use. As explained by the Supreme Court, a claim directed to a judicial exception cannot be made eligible "simply by having the applicant acquiesce to limiting the reach of the patent for the formula to a particular technological use." Diamond v. Diehr, 450 U.S. 175, 192 n.14, 209 USPQ 1, 10 n. 14 (1981). Thus, limitations that amount to merely indicating a field of use or technological environment in which to apply a judicial exception do not integrate a judicial exception into a practical application.
Step 2B
Regarding the “wherein the plurality of datasets associated with each entity include one or more of: a claims dataset; a lab dataset and/or a pharmacy dataset; or a complications dataset” limitation, as discussed above, the additional element of a data gathering step is recited at a high level of generality and amounts to extra-solution activity of receiving data, i.e. pre-solution activity of gathering data for use in the claimed process. The courts have found limitations directed to obtaining information electronically, recited at a high level of generality, to be well-understood, routine, and conventional (see MPEP 2106.05(d)(II), “receiving or transmitting data over a network”, "electronic record keeping," and "storing and retrieving information in memory"). Moreover, such limitation amounts to no more than generally linking the use of a judicial exception to a particular technological environment or field of use as explained above, which does not amount to significantly more than the judicial exception. MPEP 2106.05(h).
Regarding Claim 5
Step 2A, Prong 1
wherein, when the specific condition determined for an entity of the plurality of entities is the non-condition, determining the specific condition associated with the entity comprises: (under the broadest reasonable interpretation, a human such as a medical physician can mentally determine that the patient does not have a particular condition)
determining an absence of one or more classification codes in the claims dataset associated with the entity; and (under the broadest reasonable interpretation, a human can mentally review a claims dataset and determine that a classification code is absent)
determining at least one of one or more condition criteria is not met based on at least one of the lab dataset, the pharmacy dataset, or the complications dataset. (under the broadest reasonable interpretation, a human can mentally review data from at least one of a lab dataset, a pharmacy dataset, or a complications dataset and determine that particular condition criteria is not met)
Regarding Step 2A, Prong 2, the claim does not include any additional elements that integrate the judicial exception into a practical application and regarding Step 2B, there are no additional elements recited that amount to significantly more than the judicial exception.
Regarding Claim 6
Step 2A, Prong 1
wherein, when the specific condition determined for an entity of the plurality of entities is the undocumented condition, (under the broadest reasonable interpretation, a human such as a medical physician can mentally determine that the patient was not previously diagnosed with a particular condition)
determining the specific condition associated with the entity comprises: determining an absence of one or more classification codes in the claims dataset associated with the entity; and (under the broadest reasonable interpretation, a human can mentally review a claims dataset and determine that a classification code is absent)
determining one or more condition criteria are met based on at least one of the lab dataset, the pharmacy dataset, or the complications dataset. (under the broadest reasonable interpretation, a human can mentally review data from at least one of a lab dataset, a pharmacy dataset, or a complications dataset and determine that particular condition criteria is met)
Regarding Step 2A, Prong 2, the claim does not include any additional elements that integrate the judicial exception into a practical application and regarding Step 2B, there are no additional elements recited that amount to significantly more than the judicial exception.
Regarding Claim 7
Step 2A, Prong 1
wherein, when the specific condition determined for an entity of the plurality of entities is the delayed documented condition, (under the broadest reasonable interpretation, a human such as a medical physician can mentally determine that the patient has a condition, but that the diagnosis is too late for medical treatment to be effective)
determining the specific condition associated with the entity comprises: determining a presence of one or more classification codes in the claims dataset associated with the entity; (under the broadest reasonable interpretation, a human can mentally review a claims dataset and determine that a classification code is present)
determining one or more condition criteria are met based on at least one of the lab dataset, the pharmacy dataset, or the complications dataset; and (under the broadest reasonable interpretation, a human can mentally review data from at least one of a lab dataset, a pharmacy dataset, or a complications dataset and determine that particular condition criteria is met)
determining that a condition was documented after a pre-determined time period. (under the broadest reasonable interpretation, a human such as a medical physician can mentally determine that the patient has a condition based on a pre-determined period of time (e.g., symptoms present for at least 1 day), but that the diagnosis is too late for medical treatment to be effective)
Regarding Step 2A, Prong 2, the claim does not include any additional elements that integrate the judicial exception into a practical application and regarding Step 2B, there are no additional elements recited that amount to significantly more than the judicial exception.
Regarding Claim 8
Step 2A, Prong 1
wherein the identifier generated for an entity includes: a first value if the specific condition determined for the entity is the undocumented condition or the delayed documented condition, or a second value if the specific condition determined for the entity is the non-condition. (under the broadest reasonable interpretation, a human can mentally write down an identifier that has a first value (1) if the condition is undocumented or delayed documented, or a second value (2) if the specific value is the non-condition)
Regarding Step 2A, Prong 2, the claim does not include any additional elements that integrate the judicial exception into a practical application and regarding Step 2B, there are no additional elements recited that amount to significantly more than the judicial exception.
Regarding Claim 9
Step 2A, Prong 2
Regarding the “wherein the historical data includes at least one of: claims data; electronic medical records; lab or pharmacy data; entity demographics data; provider demographics data; social determinants of health (SDOH) data; or entity adherence data” limitation, such additional element of a data gathering step is recited at a high level of generality and amounts to extra-solution activity of receiving data, i.e. pre-solution activity of gathering data for use in the claimed process (see MPEP 2106.05(g)). Moreover, this just related to particular types of information stored in databases, and therefore such limitation amounts to no more than generally linking the use of a judicial exception to a particular technological environment or field of use. As explained by the Supreme Court, a claim directed to a judicial exception cannot be made eligible "simply by having the applicant acquiesce to limiting the reach of the patent for the formula to a particular technological use." Diamond v. Diehr, 450 U.S. 175, 192 n.14, 209 USPQ 1, 10 n. 14 (1981). Thus, limitations that amount to merely indicating a field of use or technological environment in which to apply a judicial exception do not integrate a judicial exception into a practical application.
Step 2B
Regarding the “wherein the historical data includes at least one of: claims data; electronic medical records; lab or pharmacy data; entity demographics data; provider demographics data; social determinants of health (SDOH) data; or entity adherence data” limitation, as discussed above, the additional element of a data gathering step is recited at a high level of generality and amounts to extra-solution activity of receiving data, i.e. pre-solution activity of gathering data for use in the claimed process. The courts have found limitations directed to obtaining information electronically, recited at a high level of generality, to be well-understood, routine, and conventional (see MPEP 2106.05(d)(II), “receiving or transmitting data over a network”, "electronic record keeping," and "storing and retrieving information in memory"). Moreover, such limitation amounts to no more than generally linking the use of a judicial exception to a particular technological environment or field of use as explained above, which does not amount to significantly more than the judicial exception. MPEP 2106.05(h).
Regarding Claim 10
Step 2A, Prong 2
Regarding the “wherein the machine-learning model is a classification model using a knowledge graph” limitation, such limitation amounts to no more than generally linking the use of a judicial exception to a particular technological environment or field of use (a particular type of ML model (classifier) operating on particular types of data (knowledge graphs). As explained by the Supreme Court, a claim directed to a judicial exception cannot be made eligible "simply by having the applicant acquiesce to limiting the reach of the patent for the formula to a particular technological use." Diamond v. Diehr, 450 U.S. 175, 192 n.14, 209 USPQ 1, 10 n. 14 (1981). Thus, limitations that amount to merely indicating a field of use or technological environment in which to apply a judicial exception do not integrate a judicial exception into a practical application.
Step 2B
Regarding the “wherein the machine-learning model is a classification model using a knowledge graph” limitation, such limitation amounts to no more than generally linking the use of a judicial exception to a particular technological environment or field of use as explained above, which does not amount to significantly more than the judicial exception. MPEP 2106.05(h).
Regarding Claim 11
Step 2A, Prong 1
Claim 11 recites a system that corresponds to the method of claim 1, and therefore the analysis under Step 2A, Prong 1 with respect to claim 1 also applies to this claim 11. While claim 11 recites additional generic computing components (“processors”, “computing system”, “non-transitory computer readable medium”, and “machine-learning model”), such additional generic computing components do not change the analysis under Step 2A, Prong 1.
Step 2A, Prong 2
Claim 11 recites a system that corresponds to the method of claim 1, and therefore the analysis under Step 2A, Prong 2 with respect to claim 1 also applies to this claim 11. While claim 11 recites additional generic computing components (“processors”, “computing system”, “non-transitory computer readable medium”, and “machine-learning model”), such additional generic computing components do not change the analysis under Step 2A, Prong 2. (See MPEP 2106.05(f)).
Step 2B
Claim 11 recites a system that corresponds to the method of claim 1, and therefore the analysis under Step 2B with respect to claim 1 also applies to this claim 11. While claim 11 recites additional generic computing components (“processors”, “computing system”, “non-transitory computer readable medium”, and “machine-learning model”), such additional generic computing components do not change the analysis under Step 2B. (See MPEP 2106.05(f)).
Claims 12-17 depend from claim 11 and correspond to the methods of claims 2-7, respectively, and are therefore rejected for the same reasons explained above with respect to claim 11 and claims 2-7, respectively.
Regarding Claim 18
Step 2A, Prong 1
Claim 18 recites a non-transitory computer readable medium that corresponds to the method of claim 1, and therefore the analysis under Step 2A, Prong 1 with respect to claim 1 also applies to this claim 18. While claim 18 recites additional generic computing components (“processors”, “computing system”, “non-transitory computer readable medium”, and “machine-learning model”), such additional generic computing components do not change the analysis under Step 2A, Prong 1.
Step 2A, Prong 2
Claim 18 recites a non-transitory computer readable medium that corresponds to the method of claim 1, and therefore the analysis under Step 2A, Prong 2 with respect to claim 1 also applies to this claim 18. While claim 18 recites additional generic computing components (“processors”, “computing system”, “non-transitory computer readable medium”, and “machine-learning model”), such additional generic computing components do not change the analysis under Step 2A, Prong 2. (See MPEP 2106.05(f)).
Step 2B
Claim 18 recites a non-transitory computer readable medium that corresponds to the method of claim 1, and therefore the analysis under Step 2B 1 with respect to claim 1 also applies to this claim 18. While claim 18 recites additional generic computing components (“processors”, “computing system”, “non-transitory computer readable medium”, and “machine-learning model”), such additional generic computing components do not change the analysis under Step 2B. (See MPEP 2106.05(f)).
Claims 19-20 depend from claim 18 and correspond to the methods of claims 2-3, respectively, and are therefore rejected for the same reasons explained above with respect to claim 18 and claims 2-3, respectively.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The 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 1-4, 8-9, 11-14, and 18-20 are rejected under 35 U.S.C. 103 as being unpatentable over US 11621081 B1, hereinafter referenced as O’KEEFE, in view of US 20230268051 A1, hereinafter referenced as WACHS.
Regarding Claim 1
O’KEEFE teaches:
A computer-implemented method comprising: (O’KEEFE, col. 2, lines 28-31: “One aspect of the subject matter described in this specification can be embodied in a computer-implemented method performed using a neural network comprising multiple neural network layers.”)
receiving, by one or more processors, historical data associated with a target entity from a plurality of data sources; (O’KEEFE, col. 6, lines 6-10: “System 100 generally includes data sequencers 110, 120, 130, a first neural network 140, and a second neural network 160. Sequencers 110, 120, 130 are each configured to: i) receive a set of data relating to healthcare transactions for a patient”;
O’KEEFE, col. 13, lines 19-23: “Computing device 500 includes a processor 502, memory 504, a storage device 506, a high-speed interface 508 connecting to memory 504 and high-speed expansion ports 510, and a low speed interface 512 connecting to low speed bus 514 and storage device 506.”)
deriving, by the one or more processors, one or more features from the historical data; (O’KEEFE, col. 6, lines 26-34: “The neural networks process the training data to identify, infer, or otherwise determine the most important features (e.g., lab values, diagnosis codes, EMR notes, etc.) for predicting an undiagnosed condition that affects a patient. In some implementations, the neural networks identify the most important features based on a machine learning algorithm that determines commonalities (e.g., health related commonalities) across patients using available data in the training data set.”;
O’KEEFE, col. 7, lines 45-48: “As discussed above, input data 102 for a set of subjects 102 is uniquely structured in a sequenced format, e.g., using data sequencers 110, 120, 130, so as to enhance a feature engineering process of the predictive model.”)
determining, by the one or more processors, a condition of the target entity by applying the one or more features to a machine-learning model, (O’KEEFE, col. 8, lines 13-24: “The prediction model 165 is configured to automatically identify or detect, as well as analyze various risk factors and diagnosis codes that are present in each of the respective data sequences 190 to identify undiagnosed/at-risk patients. In some implementations, the prediction model 165 is configured to identify a current undiagnosed medical condition for any desired indications or diseases. In other implementations, the prediction model 165 is configured to identify a future medical condition for any desired indications or diseases that may otherwise go undiagnosed in a set of at-risk patients.”;
O’KEEFE, col. 9, lines 36-52: “The prediction model 165 is configured to determine a confidence that an individual has the particular healthcare condition. In some implementations, the model is configured to determine a confidence that the individual has the condition and that the condition has not yet been diagnosed. Hence, scoring model 165 is configured to infer, detect, or otherwise predict one or more undiagnosed conditions that are presently affecting a patient. In other implementations, the system 100 is configured to predict one or more future healthcare conditions that will affect the individual based on analysis of prior healthcare data associated with the individual. As discussed in more detail below, the prediction model 165 can generate a confidence score (e.g., a numerical score) that is associated with an indication about an undiagnosed condition. Hence, the prediction model 165 can be a scoring model 165 that generates an output score to indicate an undiagnosed condition.”
wherein the machine-learning model has been trained by: (O’KEEFE, col. 7, lines 32-36: “Neural network 140 processes the training data provided as an output of the third data sequencer 130 to generate a hybrid vector dataset 150. Each vector dataset 150 is provided to, and processed at, a second neural network 160 to generate a prediction model 165.”;
O’KEEFE, col. 8, lines 1-4: “The trained prediction model 165 can receive data sequences 175 that are derived from scoring data 170 and a user can input a test query to obtain a prediction score.”)
receiving a plurality of datasets associated with each entity of a plurality of entities; (O’KEEFE, col. 6, lines 19-34: “Sequences of data can represent training data used to train at least one neural network of system 100. For example, a training data set can define a group of diagnosed patients that each have a particular disease being evaluated. Multiple respective training data sets can be generated such that neural networks of system 100 are trained using an expansive dataset of information that includes all available data for healthcare events involving a given set of patients. The neural networks process the training data to identify, infer, or otherwise determine the most important features (e.g., lab values, diagnosis codes, EMR notes, etc.) for predicting an undiagnosed condition that affects a patient. In some implementations, the neural networks identify the most important features based on a machine learning algorithm that determines commonalities (e.g., health related commonalities) across patients using available data in the training data set.”;
Examiner’s Note: each patient of a plurality of patients corresponds to recited each “entity of a plurality of entities”)
determining a specific condition associated with each entity of the plurality of entities based on the plurality of datasets; (O’KEEFE, col. 6, lines 19-34: “Sequences of data can represent training data used to train at least one neural network of system 100. For example, a training data set can define a group of diagnosed patients that each have a particular disease being evaluated. Multiple respective training data sets can be generated such that neural networks of system 100 are trained using an expansive dataset of information that includes all available data for healthcare events involving a given set of patients. The neural networks process the training data to identify, infer, or otherwise determine the most important features (e.g., lab values, diagnosis codes, EMR notes, etc.) for predicting an undiagnosed condition that affects a patient. In some implementations, the neural networks identify the most important features based on a machine learning algorithm that determines commonalities (e.g., health related commonalities) across patients using available data in the training data set.”)
generating an identifier for each entity of the plurality of entities based on the determined specific condition; (O’KEEFE, col. 9, lines 53-57: “The system 100 obtains patient scoring data 170 and uses at least one data sequencer 110, 120, 130 to generate data sequences 175 for determining the confidence that the individual has the particular healthcare condition using the scoring model (208).”;
Examiner’s Note: the data sequence 175 for each patient corresponds to the recited “identifier”)
deriving one or more training features for each entity of the plurality of entities from historical training data associated with the entity; and (O’KEEFE, col. 6, lines 19-34: “Sequences of data can represent training data used to train at least one neural network of system 100. For example, a training data set can define a group of diagnosed patients that each have a particular disease being evaluated. Multiple respective training data sets can be generated such that neural networks of system 100 are trained using an expansive dataset of information that includes all available data for healthcare events involving a given set of patients. The neural networks process the training data to identify, infer, or otherwise determine the most important features (e.g., lab values, diagnosis codes, EMR notes, etc.) for predicting an undiagnosed condition that affects a patient. In some implementations, the neural networks identify the most important features based on a machine learning algorithm that determines commonalities (e.g., health related commonalities) across patients using available data in the training data set.”;
O’KEEFE, col. 12, lines 61-63: “Training data 404 is provided to train the neural networks of system 100 to identify certain important features for detecting one or more undiagnosed conditions in a patient.”)
inputting the identifier and the one or more training features for each entity... (O’KEEFE, col. 6, lines 43-51: “The training data set represented by the first sequence of data is provided to the neural network 140 for processing through one or more layers of the neural network 140. In some implementations, the first data sequencer 110 is a procedure product diagnosis (PPD) data sequencer that generates a PPD training data set. Neural network 140 processes the training data provided as an output of the PPD data sequencer 110 to generate a PPD vector dataset 150.”;
O’KEEFE, col. 7, lines 45-56: “As discussed above, input data 102 for a set of subjects 102 is uniquely structured in a sequenced format, e.g., using data sequencers 110, 120, 130, so as to enhance a feature engineering process of the predictive model. In some implementations, parameter values and other detailed information associated with the procedure, the product, and the diagnosis in an example PPD sequence are encoded as a vector based on an example encoding rule. The encoding rule is obtained based on learned inferences that are determined when the neural network 140 (e.g., a deep neural network) processes one or more of the training datasets generated at least by PPD data sequencer 110.”
O’KEEFE, col. 8, lines 34-50: “System 100 can be configured to include a feedback loop 155 where encoded vector outputs may be fed back as inputs to system 100 to ensure full capture of discrete parameters in a set of information processed at the data sequencers. In some implementations, the system 100 is configured to iteratively enhance its prediction capabilities by using the feedback loop 155 to reevaluate vector outputs to, e.g., detect commonalities that exist among a more granular set of data. In some case, the system 100 can use the data sequencers 110, 120, 130 to jointly process various claims level data with reduced computation cost and better accuracy relative to conventional systems. In general, an example training process of system 100 can be based on the feedback loop 155, in which embedded vectors (outputs) are feedback to the system 100 as inputs to the system that are then analyzed to iteratively enhance the accuracy of the parameters generated by the system 100.”
O’KEEFE, col. 8, lines 53-57: “The system 100 obtains patient scoring data 170 and uses at least one data sequencer 110, 120, 130 to generate data sequences 175 for determining the confidence that the individual has the particular healthcare condition using the scoring model (208).”;
Examiner’s Note: During training, the neural network 140 (which ultimately becomes part of the trained prediction model 165), receives all of the training data processed by the sequencers 110, 120, and 130 (including the data sequences 175, corresponding to the recited “identifier”), in order to learns system parameters
However, O’KEEFE fails to explicitly teach:
... to the machine-learning model to learn associations between the identifiers and the training features associated with the plurality of entities
The examiner notes that O’KEEFE teaches that the trained prediction model 165 learns general associations between data. However, O’KEEFE does not explicitly teach that the trained prediction model 165 learns particular associations between identifiers and training features.
However, in a related field of endeavor (machine learning models related to patient care, see para. 0012), WACHS teaches and makes obvious:
inputting the identifier and the one or more training features for each entity to the machine-learning model to learn associations between the identifiers and the training features associated with the plurality of entities (WACHS, para. 0021: “The system may include additional and alternative machine learning models. For example, the system may include a performance model 126 and/or an enhancement model 128. Additional description of these models is provided in FIGS. 2-3 below. It should be appreciated that, in some examples, the performance, enhancement, and procedure models, or a combination there of, may be combined in to a single model in which associations between gesture features, image features, step identifiers, performance scores, and other information acquired by derived is used to form predictions according to machine learning concepts.”;
Examiner’s Note: WACHS explicitly teaches determining associations between identifiers and features using a machine learning model; the O’KEEFE-WACHS combination now combines the various neural network models (140, 160) of O’KEEFE into the prediction model 165, and then has the combined model determine associations between the data sequences 175 and the engineered features, as taught by WACHS).
Before the effective filing date of the present application, it would have been obvious to one of ordinary skill in the art to combine the teachings of O’KEEFE and WACHS as explained above. As disclosed by WACHS, one of ordinary skill would have been motivated to do so in order to utilize different types of neural networks that are optimized for different data types, such that a combined model can consider both images and text data, for example. (para. 0020).
Regarding Claim 2
O’KEEFE and WACHS teach the method of claim 1 as explained above. O’KEEFE further teaches:
wherein the condition determined for the target entity indicates whether or not the target entity has an undocumented condition or a delayed documented condition. (O’KEEFE, col. 4, lines 16-20: “For example, the system can learn a set of rules for identifying the various types of health related conditions noted above (e.g., undiagnosed, misdiagnosed, early detection, disease progression, etc.)”;
O’KEEFE, col. 6, lines 26-30: “The neural networks process the training data to identify, infer, or otherwise determine the most important features (e.g., lab values, diagnosis codes, EMR notes, etc.) for predicting an undiagnosed condition that affects a patient.”)
Regarding Claim 3
O’KEEFE and WACHS teach the method of claim 1 as explained above. O’KEEFE further teaches:
wherein the specific condition determined for each entity is one of: an undocumented condition, a delayed documented condition, or a non-condition. (O’KEEFE, col. 4, lines 16-20: “For example, the system can learn a set of rules for identifying the various types of health related conditions noted above (e.g., undiagnosed, misdiagnosed, early detection, disease progression, etc.)”;
O’KEEFE, col. 6, lines 26-30: “The neural networks process the training data to identify, infer, or otherwise determine the most important features (e.g., lab values, diagnosis codes, EMR notes, etc.) for predicting an undiagnosed condition that affects a patient.”)
Regarding Claim 4
O’KEEFE and WACHS teach the method of claim 3 as explained above. O’KEEFE further teaches:
wherein the plurality of datasets associated with each entity include one or more of: a claims dataset; a lab dataset and/or a pharmacy dataset; or a complications dataset. (O’KEEFE, col. 6, lines 39-43: “For example, the first sequence of data includes information describing medical procedures (e.g., Prc A, B, or C), pharmaceutical drugs or other medical treatment products (e.g., Prod A, B, or C), or medical diagnoses (e.g., Diag A, B, or C).”;
O’KEEFE, col. 11, lines 34-42: “FIG. 3A includes Dx dataset 302 and Rx dataset 304. Dx dataset 302 represents claims data for healthcare transactions relating to a medical diagnosis, a medical procedure associated with the medical diagnosis, and a doctor or physician that is associated with the medical diagnosis, the medical procedure, or both. Rx dataset 304 represents claims data for healthcare transactions relating to a drug product and a physician that is associated with the drug product, such as a prescribing physician.”)
Regarding Claim 8
O’KEEFE and WACHS teach the method of claim 1 as explained above. O’KEEFE further teaches:
wherein the identifier generated for an entity includes: a first value if the specific condition determined for the entity is the undocumented condition or the delayed documented condition, or a second value if the specific condition determined for the entity is the non-condition. (O’KEEFE, col. 7, line 65 – col. 8, line 6: “A prediction accuracy of the model is evaluated using scoring data 170. For example, the scoring data 170 can represent a curated dataset for which all diseases and indications are known. The trained prediction model 165 can receive data sequences 175 that are derived from scoring data 170 and a user can input a test query to obtain a prediction score. The prediction model 165 can process the test query against the scoring data 170 to generate prediction scores for evaluating the accuracy of the prediction model 165.”;
O’KEEFE, col. 9, lines 47-52: “ As discussed in more detail below, the prediction model 165 can generate a confidence score (e.g., a numerical score) that is associated with an indication about an undiagnosed condition. Hence, the prediction model 165 can be a scoring model 165 that generates an output score to indicate an undiagnosed condition.”
Examiner’s Note: the received data sequences 175 (corresponding to recited “identifier”) can provide a first value (e.g., greater than 50%) or a second value (e.g. less than 50%) depending on the numerical confidence score
Regarding Claim 9
O’KEEFE and WACHS teach the method of claim 1 as explained above. O’KEEFE further teaches:
wherein the historical data includes at least one of: claims data; electronic medical records; lab or pharmacy data; entity demographics data; provider demographics data; social determinants of health (SDOH) data; or entity adherence data. (O’KEEFE, col. 6, lines 39-43: “For example, the first sequence of data includes information describing medical procedures (e.g., Prc A, B, or C), pharmaceutical drugs or other medical treatment products (e.g., Prod A, B, or C), or medical diagnoses (e.g., Diag A, B, or C).”;
O’KEEFE, col. 11, lines 34-42: “FIG. 3A includes Dx dataset 302 and Rx dataset 304. Dx dataset 302 represents claims data for healthcare transactions relating to a medical diagnosis, a medical procedure associated with the medical diagnosis, and a doctor or physician that is associated with the medical diagnosis, the medical procedure, or both. Rx dataset 304 represents claims data for healthcare transactions relating to a drug product and a physician that is associated with the drug product, such as a prescribing physician.”)
Regarding Claim 11
O’KEEFE teaches:
A system comprising: one or more processors of a computing system; and at least one non-transitory computer readable medium storing instructions which, when executed by the one or more processors, cause the one or more processors to perform operations comprising: (O’KEEFE, col. 13, lines 19-31: “Computing device 500 includes a processor 502, memory 504, a storage device 506, a high-speed interface 508 connecting to memory 504 and high-speed expansion ports 510, and a low speed interface 512 connecting to low speed bus 514 and storage device 506. Each of the components 502, 504, 506, 508, 510, and 512, are interconnected using various busses, and may be mounted on a common motherboard or in other manners as appropriate. The processor 502 can process instructions for execution within the computing device 500, including instructions stored in the memory 504 or on the storage device 506 to display graphical information for a GUI on an external input/output device, such as display 516 coupled to high speed interface 508.”)
The remaining limitations correspond to the method of claim 1, and therefore this claim 11 is rejected for the same reasons explained above with respect to claim 1.
Claim 12 depends from claim 11 and corresponds to the method of claim 2 and is therefore rejected for the same reasons explained above with respect to claims 2 and 11.
Claim 13 depends from claim 11 and corresponds to the method of claim 3 and is therefore rejected for the same reasons explained above with respect to claims 3 and 11.
Claim 14 depends from claim 13 and corresponds to the method of claim 4 and is therefore rejected for the same reasons explained above with respect to claims 4 and 13.
Regarding Claim 18
O’KEEFE teaches:
A non-transitory computer readable medium, the non-transitory computer readable medium storing instructions which, when executed by one or more processors of a computing system, cause the one or more processors to perform operations comprising: (O’KEEFE, col. 13, lines 19-31: “Computing device 500 includes a processor 502, memory 504, a storage device 506, a high-speed interface 508 connecting to memory 504 and high-speed expansion ports 510, and a low speed interface 512 connecting to low speed bus 514 and storage device 506. Each of the components 502, 504, 506, 508, 510, and 512, are interconnected using various busses, and may be mounted on a common motherboard or in other manners as appropriate. The processor 502 can process instructions for execution within the computing device 500, including instructions stored in the memory 504 or on the storage device 506 to display graphical information for a GUI on an external input/output device, such as display 516 coupled to high speed interface 508.”)
The remaining limitations correspond to the method of claim 1, and therefore this claim 18 is rejected for the same reasons explained above with respect to claim 1.
Claim 19 depends from claim 18 and corresponds to the method of claim 2 and is therefore rejected for the same reasons explained above with respect to claims 2 and 18.
Claim 20 depends from claim 18 and corresponds to the method of claim 3 and is therefore rejected for the same reasons explained above with respect to claims 3 and 18.
Claims 5-6 and 15-16 are rejected under 35 U.S.C. 103 as being unpatentable over O’KEEFE in view of WACHS and further in view of US 20230133829 A1, hereinafter referenced as KUMAR, and further in view of US 20210027896 A1, hereinafter referenced as EUN.
Regarding Claim 5
O’KEEFE and WACHS teach the method of claim 4 as explained above. However, O’KEEFE and WACHS fail to explicitly teach:
wherein, when the specific condition determined for an entity of the plurality of entities is the non-condition, determining the specific condition associated with the entity comprises: determining an absence of one or more classification codes in the claims dataset associated with the entity; and
determining at least one of one or more condition criteria is not met based on at least one of the lab dataset, the pharmacy dataset, or the complications dataset.
However, in a related field of endeavor (machine learning techniques for analyzing medical data, see para. 0064), KUMAR teaches and makes obvious:
wherein, when the specific condition determined for an entity of the plurality of entities is the non-condition, determining the specific condition associated with the entity comprises: determining an absence of one or more classification codes in the claims dataset associated with the entity; and (KUMAR, para. 0140: “In one or more further examples, the health insurance claims data 818 may indicate one or more columns of one or more database tables stored by the integrated data repository 104 to analyze to determine the presence or absence of one or more health insurance codes.”;
Examiner’s Note: the O’KEEFE-WACHS-KUMAR combination now determines if a specific condition is not likely as in O’KEEFE (e.g., the score is too low and does not support the patient having the condition), and validates such finding by looking at claims data as in KUMAR to see if there is an absence of a particular claim)
Before the effective filing date of the present application, it would have been obvious to one of ordinary skill in the art to combine the teachings of O’KEEFE, WACHS, and KUMAR as explained above. As disclosed by KUMAR, one of ordinary skill would have been motivated to do so in order to verify a health condition before determining if a particular line of therapy should be approved. (para. 0140).
However, O’KEEFE, WACHS, and KUMAR fail to explicitly teach:
determining at least one of one or more condition criteria is not met based on at least one of the lab dataset, the pharmacy dataset, or the complications dataset.
However, in a related field of endeavor (machine learning with respect to healthcare, see para. 0002), EUN teaches and makes obvious:
determining at least one of one or more condition criteria is not met based on at least one of the lab dataset, the pharmacy dataset, or the complications dataset. (EUN, para. 0059: “As illustrated in FIG. 3, a cohort 304 of patients 306 that are at risk of, or are in the early stages of RA, may be identified out of a larger subset 300 of patients with any RA diagnosis (e.g., by excluding patients 302 in the larger subset 300 having been misdiagnosed, which may be determined by another, subsequent, conflicting, or overriding diagnosis in the patients' medical record or based on other exclusion criteria such as lab tests or procedures that indicate a different diagnosis).”;
Examiner’s Note: the O’KEEFE-WACHS-KUMAR-EUN combination now uses lab tests to determine if a patient has been correctly diagnosed, or if there should be a different diagnosis)
Before the effective filing date of the present application, it would have been obvious to one of ordinary skill in the art to combine the teachings of O’KEEFE, WACHS, KUMAR, and EUN as explained above. As disclosed by EUN, one of ordinary skill would have been motivated to do so in order to determine if there is a conflicting or overriding diagnosis that should be made based on other available data. (para. 0059).
Regarding Claim 6
O’KEEFE and WACHS teach the method of claim 4 as explained above. However, O’KEEFE and WACHS fail to explicitly teach:
wherein, when the specific condition determined for an entity of the plurality of entities is the undocumented condition, determining the specific condition associated with the entity comprises: determining an absence of one or more classification codes in the claims dataset associated with the entity; and
determining one or more condition criteria are met based on at least one of the lab dataset, the pharmacy dataset, or the complications dataset.
However, in a related field of endeavor (machine learning techniques for analyzing medical data, see para. 0064), KUMAR teaches and makes obvious:
wherein, when the specific condition determined for an entity of the plurality of entities is the undocumented condition, determining the specific condition associated with the entity comprises: determining an absence of one or more classification codes in the claims dataset associated with the entity; and (KUMAR, para. 0140: “In one or more further examples, the health insurance claims data 818 may indicate one or more columns of one or more database tables stored by the integrated data repository 104 to analyze to determine the presence or absence of one or more health insurance codes.”;
Examiner’s Note: the O’KEEFE-WACHS-KUMAR combination now determines if there is an undiagnosed condition as in O’KEEFE and validates such finding by looking at claims data as in KUMAR to see if there is an absence of a particular claim)
Before the effective filing date of the present application, it would have been obvious to one of ordinary skill in the art to combine the teachings of O’KEEFE, WACHS, and KUMAR as explained above. As disclosed by KUMAR, one of ordinary skill would have been motivated to do so in order to verify a health condition before determining if a particular line of therapy should be approved. (para. 0140).
However, O’KEEFE, WACHS, and KUMAR fail to explicitly teach:
determining one or more condition criteria are met based on at least one of the lab dataset, the pharmacy dataset, or the complications dataset.
However, in a related field of endeavor (machine learning with respect to healthcare, see para. 0002), EUN teaches and makes obvious:
determining one or more condition criteria are met based on at least one of the lab dataset, the pharmacy dataset, or the complications dataset. (EUN, para. 0059: “As illustrated in FIG. 3, a cohort 304 of patients 306 that are at risk of, or are in the early stages of RA, may be identified out of a larger subset 300 of patients with any RA diagnosis (e.g., by excluding patients 302 in the larger subset 300 having been misdiagnosed, which may be determined by another, subsequent, conflicting, or overriding diagnosis in the patients' medical record or based on other exclusion criteria such as lab tests or procedures that indicate a different diagnosis).”;
Examiner’s Note: the O’KEEFE-WACHS-KUMAR-EUN combination now uses lab tests to determine if a patient has been correctly diagnosed, or if there should be a different diagnosis)
Before the effective filing date of the present application, it would have been obvious to one of ordinary skill in the art to combine the teachings of O’KEEFE, WACHS, KUMAR, and EUN as explained above. As disclosed by EUN, one of ordinary skill would have been motivated to do so in order to determine if there is a conflicting or overriding diagnosis that should be made based on other available data. (para. 0059).
Claim 15 depends from claim 14 and corresponds to the method of claim 5 and is therefore rejected for the same reasons explained above with respect to claims 5 and 14.
Claim 16 depends from claim 14 and corresponds to the method of claim 6 and is therefore rejected for the same reasons explained above with respect to claims 6 and 14.
Claims 7 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over O’KEEFE in view of WACHS, KUMAR, and EUN and further in view of US 20220344020 A1, hereinafter referenced as VANNESS.
Regarding Claim 5
O’KEEFE and WACHS teach the method of claim 4 as explained above. However, O’KEEFE and WACHS fail to explicitly teach:
when the specific condition determined for an entity of the plurality of entities is the delayed documented condition,
determining the specific condition associated with the entity comprises: determining a presence of one or more classification codes in the claims dataset associated with the entity;
determining one or more condition criteria are met based on at least one of the lab dataset, the pharmacy dataset, or the complications dataset; and
determining that a condition was documented after a pre-determined time period.
However, in a related field of endeavor (machine learning techniques for analyzing medical data, see para. 0064), KUMAR teaches and makes obvious:
determining the specific condition associated with the entity comprises: determining a presence of one or more classification codes in the claims dataset associated with the entity;
(KUMAR, para. 0140: “In one or more further examples, the health insurance claims data 818 may indicate one or more columns of one or more database tables stored by the integrated data repository 104 to analyze to determine the presence or absence of one or more health insurance codes.”;
Examiner’s Note: the O’KEEFE-WACHS-KUMAR combination now validates medical findings by looking at claims data as in KUMAR to see if there is an absence or presence of a particular claim)
Before the effective filing date of the present application, it would have been obvious to one of ordinary skill in the art to combine the teachings of O’KEEFE, WACHS, and KUMAR as explained above. As disclosed by KUMAR, one of ordinary skill would have been motivated to do so in order to verify a health condition before determining if a particular line of therapy should be approved. (para. 0140).
However, O’KEEFE, WACHS, and KUMAR fail to explicitly teach:
when the specific condition determined for an entity of the plurality of entities is the delayed documented condition,
determining one or more condition criteria are met based on at least one of the lab dataset, the pharmacy dataset, or the complications dataset; and
determining that a condition was documented after a pre-determined time period.
However, in a related field of endeavor (machine learning with respect to healthcare, see para. 0002), EUN teaches and makes obvious:
determining one or more condition criteria are met based on at least one of the lab dataset, the pharmacy dataset, or the complications dataset; and (EUN, para. 0059: “As illustrated in FIG. 3, a cohort 304 of patients 306 that are at risk of, or are in the early stages of RA, may be identified out of a larger subset 300 of patients with any RA diagnosis (e.g., by excluding patients 302 in the larger subset 300 having been misdiagnosed, which may be determined by another, subsequent, conflicting, or overriding diagnosis in the patients' medical record or based on other exclusion criteria such as lab tests or procedures that indicate a different diagnosis).”;
Examiner’s Note: the O’KEEFE-WACHS-KUMAR-EUN combination now uses lab tests to determine if a patient has been correctly diagnosed, or if there should be a different diagnosis)
Before the effective filing date of the present application, it would have been obvious to one of ordinary skill in the art to combine the teachings of O’KEEFE, WACHS, KUMAR, and EUN as explained above. As disclosed by EUN, one of ordinary skill would have been motivated to do so in order to determine if there is a conflicting or overriding diagnosis that should be made based on other available data. (para. 0059).
However, O’KEEFE, WACHS, KUMAR, and EUN fail to explicitly teach:
when the specific condition determined for an entity of the plurality of entities is the delayed documented condition,
determining that a condition was documented after a pre-determined time period.
However, in a related field of endeavor (computerized methods of analyzing patient health data, see para. 0015), VANNESS teaches and makes obvious:
when the specific condition determined for an entity of the plurality of entities is the delayed documented condition, (VANNESS, para. 0091: “When the medical laboratory result reports a SCr above 1.40 mg/dl, the hospital reacts and treats the kidney injury as acute based upon the rise in SCr value. In the absence or neglect of prior values, the hospital is unable or late in the timely diagnosis and treatment of acute kidney injury as the clinical diagnosis of acute kidney injury is an increase of SCr values by >0.3 mg/dl over a 48 hour time period.”;
Examiner’s Note: the O’KEEFE-WACHS-KUMAR-EUN-VANNESS combination now verifies that an undiagnosed condition is present and that such diagnosis is late as in VANNESS)
determining that a condition was documented after a pre-determined time period. (VANNESS, para. 0091: “When the medical laboratory result reports a SCr above 1.40 mg/dl, the hospital reacts and treats the kidney injury as acute based upon the rise in SCr value. In the absence or neglect of prior values, the hospital is unable or late in the timely diagnosis and treatment of acute kidney injury as the clinical diagnosis of acute kidney injury is an increase of SCr values by >0.3 mg/dl over a 48 hour time period.”;
Examiner’s Note: the O’KEEFE-WACHS-KUMAR-EUN-VANNESS combination now verifies that an undiagnosed condition is present and that such diagnosis is late as in VANNESS because a certain time period has been exceeded with respect to certain lab values)
Before the effective filing date of the present application, it would have been obvious to one of ordinary skill in the art to combine the teachings of O’KEEFE, WACHS, KUMAR, EUN, and VANNESS as explained above. As disclosed by VANNESS, one of ordinary skill would have been motivated to do so in order to determine if there is an updated condition that can be charged for medical billing. (para. 0091).
Claim 17 depends from claim 14 and corresponds to the method of claim 7 and is therefore rejected for the same reasons explained above with respect to claims 7 and 14.
Claim 10 is rejected under 35 U.S.C. 103 as being unpatentable over O’KEEFE in view of WACHS and further in view of US 20240038083 A1, hereinafter referenced as LI.
Regarding Claim 10
O’KEEFE and WACHS teach the method of claim 1 as explained above. However, O’KEEFE and WACHS fail to explicitly teach:
wherein the machine-learning model is a classification model using a knowledge graph.
However, in a related field of endeavor (technical data collection with respect to patient data, see paras. 0002-0003), LI teaches and makes obvious:
wherein the machine-learning model is a classification model using a knowledge graph. (LI, paras.0008-0014: “The present disclosure adopts a technical solution as follows: [0009] a publicity-education pushing method based on a multi-source information fusion includes the following steps: [0010] step S1: constructing a patient publicity-education knowledge graph through public knowledge, a clinical expert supplement and an electronic medical record, and pushing the patient publicity-education knowledge graph to a patient through a publicity-education applet; ... [0012] step S3: constructing a compliance prediction model through a neural network by using the patient multi-source information and data collected on patient medication-taking behavior; [0013] step S4: predicting a patient category by using the compliance prediction model to obtain a patient classification; and [0014] step S5: building a system rule base by using the patient multi-source information, and after searching for a corresponding disease and treatment in the patient publicity-education knowledge graph through feedback information from the system rule base, pushing the disease and the treatment to the patient through the publicity-education applet.”;
Examiner’s Note: the O’KEEFE-WACHS-LI combination now modifies the machine learning predictive model of O’KEEFE to also output classifications and to operate on knowledge graph information as in LI).
Before the effective filing date of the present application, it would have been obvious to one of ordinary skill in the art to combine the teachings of O’KEEFE, WACHS, and LI as explained above. As disclosed by LI, one of ordinary skill would have been motivated to do so because knowledge graphs are “able to store a large amount of information” and are “more accurate, efficient, professional, easy to search and apply.” (para. 0042).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
US 20190371472 A1 (Blanchard). “According to an exemplary embodiment of the present disclosure, a system for determining an undocumented comorbidity condition in a patient, is disclosed. In one embodiment, the system comprises an integrated care system configured to: extract patient data from one or more databases corresponding to a pool of patients receiving treatment; using one or more predictive models with the extracted patient data to generate, for each of the patients in the pool of patients, a respective patient risk score for having an undocumented comorbidity condition; identify a subset of the pool of patients having a respective patient risk score that is higher than a predetermined threshold value; and based on the identified subset of the pool of patients, identifying one or more patients for additional evaluation, additional review, or combinations thereof.” (para. 0022).
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MICHAEL C LEE whose telephone number is (571)272-4933. The examiner can normally be reached M-F 12:00 pm - 8:00 pm 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, Omar Fernandez Rivas can be reached at 571-272-2589. 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.
/MICHAEL C. LEE/Examiner, Art Unit 2128
Prosecution Insights