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 .
Priority
The present application has a provisional application No. 63/224,238 filed on July 21, 2021.
The present application has a preliminary amendment filed on Jan, 19, 2024 and July 15, 2024 with Claims 1-15, 22, 29, 35-36, 42 in pending.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-15, 22, 29, 35-36, 42 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Regarding Claim 1
Step 1 – whether the claim falls within any statutory category. See MPEP 2016.03
Claim 1 is a method claim thus it falls into one of the four categories of statutory subject matter.
Step 2A Prong 1 – whether the claim recites a judicial exception. See MPEP 2106.04, subsection II.
Regarding independent claim 1, following limitations recite a judicial exception:
“receiving first medical information for each of the patients, wherein the medical information includes at least one of the medical events and a time associated with the at least one of the medical events”
[Mental Process] – receiving data can be heard and seen which involves observations, evaluations, judgments, and opinions that is capable of being performed in the human mind with the assistance of paper and pen
“generating a summary of the medical information”
[Mathematical Calculations] – generating a summary of the medical information involves creating a vector to be embedded which requires mathematical computation which recites to an abstract idea
[Mental Process] – generating a summary based on the information is simply collecting and analyzing the information which involves observations, evaluations, judgments, and opinions that is capable of being performed in the human mind with the assistance of paper and pen
“generating a multivariate point process model based on the summarized medical information, wherein a computation of a non-estimated probability distribution is used to train the multivariate point process model”
[Mathematical Calculations] – generating the multivariate point process model, which is simply a model that analyzes multiple events and times on a continuous time line, based on the computation of a non-estimated probability distribution to train the model requires mathematical computation which recites to an abstract idea.
“receiving second medical information for the at least particular one of the patients”
[Mental Process] – receiving data can be heard and seen which involves observations, evaluations, judgments, and opinions that is capable of being performed in the human mind with the assistance of paper and pen
“predicting and facilitating at least possible one of the medical events and a predicted time of the at least possible one of the medical events for the at least particular one of the patients”
[Mathematical Calculations] – predicting these features requiring use of survival functions and history functions which requires mathematical computation which recites to an abstract idea.
[Mental Process] – using predicted information to facilitate or help a patient involves observations, evaluations, judgments, and opinions that is capable of being performed in the human mind with the assistance of paper and pen
Step 2A Prong 2 – whether the claim recites additional elements that integrate the exception into a practical application of the exception?
The claim 1 does not recite any additional elements other than abstract ideas, so it does not integrate into a practical application. Thus, this claim is directed to the abstract idea.
Regarding Claim 2
Step 1 – whether the claim falls within any statutory category. See MPEP 2016.03
Claim 2 is a dependent claim of 1, thus it falls within the same category of statutory subject matter.
Step 2A Prong 1 – whether the claim recites a judicial exception. See MPEP 2106.04, subsection II.
Regarding dependent claim 2, following limitations recite a judicial exception:
“specifying a dependence between the future time and the future event”
[Mathematical Calculations] – specifying the dependence between the two features requires use of mathematical functions and calculations which recites to an abstract idea
Step 2A Prong 2 – whether the claim recites additional elements that integrate the exception into a practical application of the exception?
The claim 2 does not recite any additional elements other than abstract ideas, so it does not integrate into a practical application. Thus, this claim is directed to the abstract idea.
Regarding Claim 3
Step 1 – whether the claim falls within any statutory category. See MPEP 2016.03
Claim 3 is a dependent claim of 1, thus it falls within the same category of statutory subject matter.
Step 2A Prong 1 – whether the claim recites a judicial exception. See MPEP 2106.04, subsection II.
Regarding dependent claim 3, following limitations recite a judicial exception:
“the multivariate point process model specifies a conditional probability of each of the medical events”
[Mathematical Calculations] – specifying the conditional probabilities for each medical event requires use of mathematical functions and calculations which recites to an abstract idea
Step 2A Prong 2 – whether the claim recites additional elements that integrate the exception into a practical application of the exception?
The claim 3 does not recite any additional elements other than abstract ideas, so it does not integrate into a practical application. Thus, this claim is directed to the abstract idea.
Regarding Claim 4
Step 1 – whether the claim falls within any statutory category. See MPEP 2016.03
Claim 4 is a dependent claim of 3, thus it falls within the same category of statutory subject matter.
Step 2A Prong 1 – whether the claim recites a judicial exception. See MPEP 2106.04, subsection II.
Regarding dependent claim 4, following limitations recite a judicial exception:
“the multivariate point process model is based on a survival function and a history function which is associated with the summarized medical information”
[Mathematical Calculations] – using the survival function and the history function that is associated with the summarized medical information vector involves use of mathematical functions and calculations which recites to an abstract idea
Step 2A Prong 2 – whether the claim recites additional elements that integrate the exception into a practical application of the exception?
The claim 4 does not recite any additional elements other than abstract ideas, so it does not integrate into a practical application. Thus, this claim is directed to the abstract idea.
Regarding Claim 5
Step 1 – whether the claim falls within any statutory category. See MPEP 2016.03
Claim 5 is a dependent claim of 4, thus it falls within the same category of statutory subject matter.
Step 2A Prong 1 – whether the claim recites a judicial exception. See MPEP 2106.04, subsection II.
Regarding dependent claim 5, following limitations recite a judicial exception:
“the conditional probability is determined based on the survival function in view of the history function”
[Mathematical Calculations] – using the survival function and the history to find the conditional probability involves use of mathematical functions and calculations which recites to an abstract idea
Step 2A Prong 2 – whether the claim recites additional elements that integrate the exception into a practical application of the exception?
The claim 5 does not recite any additional elements other than abstract ideas, so it does not integrate into a practical application. Thus, this claim is directed to the abstract idea.
Regarding Claim 6
Step 1 – whether the claim falls within any statutory category. See MPEP 2016.03
Claim 6 is a dependent claim of 1, thus it falls within the same category of statutory subject matter.
Step 2A Prong 1 – whether the claim recites a judicial exception. See MPEP 2106.04, subsection II.
Regarding dependent claim 6, following limitations recite a judicial exception:
“the multivariate point process model facilitates a generation of the at least possible one of the medical events and the predicted time based on a sample from all of event distributions”
[Mathematical Calculations] – generating these events and times based on the distribution involves use of mathematical functions and calculations which recites to an abstract idea
Step 2A Prong 2 – whether the claim recites additional elements that integrate the exception into a practical application of the exception?
The claim 6 does not recite any additional elements other than abstract ideas, so it does not integrate into a practical application. Thus, this claim is directed to the abstract idea.
Regarding Claim 7
Step 1 – whether the claim falls within any statutory category. See MPEP 2016.03
Claim 7 is a dependent claim of 1, thus it falls within the same category of statutory subject matter.
Step 2A Prong 1 – whether the claim recites a judicial exception. See MPEP 2106.04, subsection II.
Regarding dependent claim 7, following limitations recite a judicial exception:
“facilitating or controlling the treatment of the at least particular one of the patients based on the generated at least possible one of the medical events and the predicted time”
[Mathematical Calculations] – generating these events and times based on the distribution involves use of mathematical functions and calculations which recites to an abstract idea
[Mental Process] – facilitating or controlling the treatment of the patients involves observations, evaluations, judgments, and opinions that is capable of being performed in the human mind with the assistance of paper and pen
Step 2A Prong 2 – whether the claim recites additional elements that integrate the exception into a practical application of the exception?
The claim 7 does not recite any additional elements other than abstract ideas, so it does not integrate into a practical application. Thus, this claim is directed to the abstract idea.
Regarding Claim 8
Step 1 – whether the claim falls within any statutory category. See MPEP 2016.03
Claim 8 is a method claim thus it falls into one of the four categories of statutory subject matter.
Step 2A Prong 1 – whether the claim recites a judicial exception. See MPEP 2106.04, subsection II.
Regarding independent claim 8, following limitations recite a judicial exception:
“receiving first medical information for each of the patients, wherein the medical information includes at least one of the medical events and a time associated with the at least one of the medical events”
[Mental Process] – receiving data can be heard and seen which involves observations, evaluations, judgments, and opinions that is capable of being performed in the human mind with the assistance of paper and pen
“generating a summary of the medical information”
[Mathematical Calculations] – generating a summary of the medical information involves creating a vector to be embedded which requires mathematical computation which recites to an abstract idea
[Mental Process] – generating a summary based on the information is simply collecting and analyzing the information which involves observations, evaluations, judgments, and opinions that is capable of being performed in the human mind with the assistance of paper and pen
“generating a multivariate point process model based on the summarized medical information, wherein each of the medical events has its own distinct sub-model which tracks progression of interevent times for that particular medical event”
[Mental Process] – generating the multivariate point process model, which is simply a model that analyzes multiple events and times on a continuous time line, where each event has its own sub-model that tracks the progression requires continuous tracking of each event over time which involves observations, evaluations, judgments, and opinions that is capable of being performed in the human mind with the assistance of paper and pen
“receiving second medical information for the at least particular one of the patients”
[Mental Process] – receiving data can be heard and seen which involves observations, evaluations, judgments, and opinions that is capable of being performed in the human mind with the assistance of paper and pen
“predicting and facilitating at least possible one of the medical events and a predicted time of the at least possible one of the medical events for the at least particular one of the patients”
[Mathematical Calculations] – predicting these features requiring use of survival functions and history functions which requires mathematical computation which recites to an abstract idea.
[Mental Process] – using predicted information to facilitate or help a patient involves observations, evaluations, judgments, and opinions that is capable of being performed in the human mind with the assistance of paper and pen
Step 2A Prong 2 – whether the claim recites additional elements that integrate the exception into a practical application of the exception?
The claim 8 does not recite any additional elements other than abstract ideas, so it does not integrate into a practical application. Thus, this claim is directed to the abstract idea.
Regarding Claim 9
Step 1 – whether the claim falls within any statutory category. See MPEP 2016.03
Claim 9 is a dependent claim of 8, thus it falls within the same category of statutory subject matter.
Step 2A Prong 1 – whether the claim recites a judicial exception. See MPEP 2106.04, subsection II.
Regarding dependent claim 9, following limitations recite a judicial exception:
“specifying a dependence between the future time and the future event”
[Mathematical Calculations] – specifying the dependence between the two features requires use of mathematical functions and calculations which recites to an abstract idea
Step 2A Prong 2 – whether the claim recites additional elements that integrate the exception into a practical application of the exception?
The claim 9 does not recite any additional elements other than abstract ideas, so it does not integrate into a practical application. Thus, this claim is directed to the abstract idea.
Regarding Claim 10
Step 1 – whether the claim falls within any statutory category. See MPEP 2016.03
Claim 10 is a dependent claim of 8, thus it falls within the same category of statutory subject matter.
Step 2A Prong 1 – whether the claim recites a judicial exception. See MPEP 2106.04, subsection II.
Regarding dependent claim 10, following limitations recite a judicial exception:
“the multivariate point process model specifies a conditional probability of each of the medical events”
[Mathematical Calculations] – specifying the conditional probabilities for each medical event requires use of mathematical functions and calculations which recites to an abstract idea
Step 2A Prong 2 – whether the claim recites additional elements that integrate the exception into a practical application of the exception?
The claim 10 does not recite any additional elements other than abstract ideas, so it does not integrate into a practical application. Thus, this claim is directed to the abstract idea.
Regarding Claim 11
Step 1 – whether the claim falls within any statutory category. See MPEP 2016.03
Claim 11 is a dependent claim of 10, thus it falls within the same category of statutory subject matter.
Step 2A Prong 1 – whether the claim recites a judicial exception. See MPEP 2106.04, subsection II.
Regarding dependent claim 11, following limitations recite a judicial exception:
“the multivariate point process model is based on a survival function and a history function which is associated with the summarized medical information”
[Mathematical Calculations] – using the survival function and the history function that is associated with the summarized medical information vector involves use of mathematical functions and calculations which recites to an abstract idea
Step 2A Prong 2 – whether the claim recites additional elements that integrate the exception into a practical application of the exception?
The claim 11 does not recite any additional elements other than abstract ideas, so it does not integrate into a practical application. Thus, this claim is directed to the abstract idea.
Regarding Claim 12
Step 1 – whether the claim falls within any statutory category. See MPEP 2016.03
Claim 12 is a dependent claim of 11, thus it falls within the same category of statutory subject matter.
Step 2A Prong 1 – whether the claim recites a judicial exception. See MPEP 2106.04, subsection II.
Regarding dependent claim 12, following limitations recite a judicial exception:
“the conditional probability is determined based on the survival function in view of the history function”
[Mathematical Calculations] – using the survival function and the history to find the conditional probability involves use of mathematical functions and calculations which recites to an abstract idea
Step 2A Prong 2 – whether the claim recites additional elements that integrate the exception into a practical application of the exception?
The claim 12 does not recite any additional elements other than abstract ideas, so it does not integrate into a practical application. Thus, this claim is directed to the abstract idea.
Regarding Claim 13
Step 1 – whether the claim falls within any statutory category. See MPEP 2016.03
Claim 13 is a dependent claim of 8, thus it falls within the same category of statutory subject matter.
Step 2A Prong 1 – whether the claim recites a judicial exception. See MPEP 2106.04, subsection II.
Regarding dependent claim 13, following limitations recite a judicial exception:
“the multivariate point process model facilitates a generation of the at least possible one of the medical events and the predicted time based on a sample from all of event distributions”
[Mathematical Calculations] – generating these events and times based on the distribution involves use of mathematical functions and calculations which recites to an abstract idea
Step 2A Prong 2 – whether the claim recites additional elements that integrate the exception into a practical application of the exception?
The claim 13 does not recite any additional elements other than abstract ideas, so it does not integrate into a practical application. Thus, this claim is directed to the abstract idea.
Regarding Claim 14
Step 1 – whether the claim falls within any statutory category. See MPEP 2016.03
Claim 14 is a dependent claim of 8, thus it falls within the same category of statutory subject matter.
Step 2A Prong 1 – whether the claim recites a judicial exception. See MPEP 2106.04, subsection II.
Regarding dependent claim 14, following limitations recite a judicial exception:
“facilitating or controlling the treatment of the at least particular one of the patients based on the generated at least possible one of the medical events and the predicted time”
[Mathematical Calculations] – generating these events and times based on the distribution involves use of mathematical functions and calculations which recites to an abstract idea
[Mental Process] – facilitating or controlling the treatment of the patients involves observations, evaluations, judgments, and opinions that is capable of being performed in the human mind with the assistance of paper and pen
Step 2A Prong 2 – whether the claim recites additional elements that integrate the exception into a practical application of the exception?
The claim 14 does not recite any additional elements other than abstract ideas, so it does not integrate into a practical application. Thus, this claim is directed to the abstract idea.
Regarding Claim 15
Step 1 – whether the claim falls within any statutory category. See MPEP 2016.03
Claim 15 is a non-transitory computer-accessible medium claim thus it falls into one of the four categories of statutory subject matter.
Step 2A Prong 1 – whether the claim recites a judicial exception. See MPEP 2106.04, subsection II.
Regarding independent claim 15, following limitations recite a judicial exception:
“receiving first medical information for each of the patients, wherein the medical information includes at least one of the medical events and a time associated with the at least one of the medical events”
[Mental Process] – receiving data can be heard and seen which involves observations, evaluations, judgments, and opinions that is capable of being performed in the human mind with the assistance of paper and pen
“generating a summary of the medical information”
[Mathematical Calculations] – generating a summary of the medical information involves creating a vector to be embedded which requires mathematical computation which recites to an abstract idea
[Mental Process] – generating a summary based on the information is simply collecting and analyzing the information which involves observations, evaluations, judgments, and opinions that is capable of being performed in the human mind with the assistance of paper and pen
“generating a multivariate point process model based on the summarized medical information, wherein a computation of a non-estimated probability distribution is used to train the multivariate point process model”
[Mathematical Calculations] – generating the multivariate point process model, which is simply a model that analyzes multiple events and times on a continuous time line, based on the computation of a non-estimated probability distribution to train the model requires mathematical computation which recites to an abstract idea.
“receiving second medical information for the at least particular one of the patients”
[Mental Process] – receiving data can be heard and seen which involves observations, evaluations, judgments, and opinions that is capable of being performed in the human mind with the assistance of paper and pen
“predicting and facilitating at least possible one of the medical events and a predicted time of the at least possible one of the medical events for the at least particular one of the patients”
[Mathematical Calculations] – predicting these features requiring use of survival functions and history functions which requires mathematical computation which recites to an abstract idea.
[Mental Process] – using predicted information to facilitate or help a patient involves observations, evaluations, judgments, and opinions that is capable of being performed in the human mind with the assistance of paper and pen
Step 2A Prong 2 – whether the claim recites additional elements that integrate the exception into a practical application of the exception?
The claim 15 does not recite any additional elements other than abstract ideas, so it does not integrate into a practical application. Thus, this claim is directed to the abstract idea.
Regarding Claim 22
Step 1 – whether the claim falls within any statutory category. See MPEP 2016.03
Claim 22 is a non-transitory computer-accessible medium claim thus it falls into one of the four categories of statutory subject matter.
Step 2A Prong 1 – whether the claim recites a judicial exception. See MPEP 2106.04, subsection II.
Regarding independent claim 22, following limitations recite a judicial exception:
“receiving first medical information for each of the patients, wherein the medical information includes at least one of the medical events and a time associated with the at least one of the medical events”
[Mental Process] – receiving data can be heard and seen which involves observations, evaluations, judgments, and opinions that is capable of being performed in the human mind with the assistance of paper and pen
“generating a summary of the medical information”
[Mathematical Calculations] – generating a summary of the medical information involves creating a vector to be embedded which requires mathematical computation which recites to an abstract idea
[Mental Process] – generating a summary based on the information is simply collecting and analyzing the information which involves observations, evaluations, judgments, and opinions that is capable of being performed in the human mind with the assistance of paper and pen
“generating a multivariate point process model based on the summarized medical information, wherein each of the medical events has its own distinct sub-model which tracks progression of interevent times for that particular medical event”
[Mental Process] – generating the multivariate point process model, which is simply a model that analyzes multiple events and times on a continuous time line, where each event has its own sub-model that tracks the progression requires continuous tracking of each event over time which involves observations, evaluations, judgments, and opinions that is capable of being performed in the human mind with the assistance of paper and pen
“receiving second medical information for the at least particular one of the patients”
[Mental Process] – receiving data can be heard and seen which involves observations, evaluations, judgments, and opinions that is capable of being performed in the human mind with the assistance of paper and pen
“predicting and facilitating at least possible one of the medical events and a predicted time of the at least possible one of the medical events for the at least particular one of the patients”
[Mathematical Calculations] – predicting these features requiring use of survival functions and history functions which requires mathematical computation which recites to an abstract idea.
[Mental Process] – using predicted information to facilitate or help a patient involves observations, evaluations, judgments, and opinions that is capable of being performed in the human mind with the assistance of paper and pen
Step 2A Prong 2 – whether the claim recites additional elements that integrate the exception into a practical application of the exception?
The claim 22 does not recite any additional elements other than abstract ideas, so it does not integrate into a practical application. Thus, this claim is directed to the abstract idea.
Regarding Claim 29
Step 1 – whether the claim falls within any statutory category. See MPEP 2016.03
Claim 29 is a system claim thus it falls into one of the four categories of statutory subject matter.
Step 2A Prong 1 – whether the claim recites a judicial exception. See MPEP 2106.04, subsection II.
Regarding independent claim 29, following limitations recite a judicial exception:
“receive first medical information for each of the patients, wherein the medical information includes at least one of the medical events and a time associated with the at least one of the medical events”
[Mental Process] – receiving data can be heard and seen which involves observations, evaluations, judgments, and opinions that is capable of being performed in the human mind with the assistance of paper and pen
“generate a summary of the medical information”
[Mathematical Calculations] – generating a summary of the medical information involves creating a vector to be embedded which requires mathematical computation which recites to an abstract idea
[Mental Process] – generating a summary based on the information is simply collecting and analyzing the information which involves observations, evaluations, judgments, and opinions that is capable of being performed in the human mind with the assistance of paper and pen
“generate a multivariate point process model based on the summarized medical information, wherein a computation of a non-estimated probability distribution is used to train the multivariate point process model”
[Mathematical Calculations] – generating the multivariate point process model, which is simply a model that analyzes multiple events and times on a continuous time line, based on the computation of a non-estimated probability distribution to train the model requires mathematical computation which recites to an abstract idea.
“receive second medical information for the at least particular one of the patients”
[Mental Process] – receiving data can be heard and seen which involves observations, evaluations, judgments, and opinions that is capable of being performed in the human mind with the assistance of paper and pen
“predict and facilitate at least possible one of the medical events and a predicted time of the at least possible one of the medical events for the at least particular one of the patients”
[Mathematical Calculations] – predicting these features requiring use of survival functions and history functions which requires mathematical computation which recites to an abstract idea.
[Mental Process] – using predicted information to facilitate or help a patient involves observations, evaluations, judgments, and opinions that is capable of being performed in the human mind with the assistance of paper and pen
Step 2A Prong 2 – whether the claim recites additional elements that integrate the exception into a practical application of the exception?
Regarding Claim 29, the claim recites additional elements of
“a computer hardware”
A computer hardware is recited at a high level of generality and is merely adding words “apply it” to the judicial exception. (see MPEP 2106.05(f))
[Even when viewed in combination, the additional elements do no more than automate the mental processes that a person could perform, using computer components as a tool, thus the claim as a whole does not integrate into a practical application.]
Step 2B – whether the claim as a whole amount to significantly more than the judicial exception? I.e. Are there any additional elements (features/limitations/step) recited in the claim beyond the abstract idea?
The claim does not provide an inventive concept (significantly more than the abstract idea). The claim is ineligible.
As explained above, the additional element [1] is considered a mere instruction to apply an exception to the generic computer components (see MPEP 2106.05(f)). This limitation remains a mere instruction to apply an exception even upon reconsideration. Even when considered in combination, the additional element represents a mere instruction to apply an exception, which cannot provide an inventive concept.
Regarding Claim 35
Step 1 – whether the claim falls within any statutory category. See MPEP 2016.03
Claim 35 is a dependent claim of 29, thus it falls within the same category of statutory subject matter.
Step 2A Prong 1 – whether the claim recites a judicial exception. See MPEP 2106.04, subsection II.
Regarding dependent claim 35, following limitations recite a judicial exception:
“facilitate or control the treatment of the at least particular one of the patients based on the generated at least possible one of the medical events and the predicted time”
[Mathematical Calculations] – generating these events and times based on the distribution involves use of mathematical functions and calculations which recites to an abstract idea
[Mental Process] – facilitating or controlling the treatment of the patients involves observations, evaluations, judgments, and opinions that is capable of being performed in the human mind with the assistance of paper and pen
Step 2A Prong 2 – whether the claim recites additional elements that integrate the exception into a practical application of the exception?
Regarding Claim 35, the claim recites additional elements of
“the computer hardware”
The computer hardware is recited at a high level of generality and is merely adding words “apply it” to the judicial exception. (see MPEP 2106.05(f))
[Even when viewed in combination, the additional elements do no more than automate the mental processes that a person could perform, using computer components as a tool, thus the claim as a whole does not integrate into a practical application.]
Step 2B – whether the claim as a whole amount to significantly more than the judicial exception? I.e. Are there any additional elements (features/limitations/step) recited in the claim beyond the abstract idea?
The claim does not provide an inventive concept (significantly more than the abstract idea). The claim is ineligible.
As explained above, the additional element [1] is considered a mere instruction to apply an exception to the generic computer components (see MPEP 2106.05(f)). This limitation remains a mere instruction to apply an exception even upon reconsideration. Even when considered in combination, the additional element represents a mere instruction to apply an exception, which cannot provide an inventive concept.
Regarding Claim 36
Step 1 – whether the claim falls within any statutory category. See MPEP 2016.03
Claim 36 is a system claim thus it falls into one of the four categories of statutory subject matter.
Step 2A Prong 1 – whether the claim recites a judicial exception. See MPEP 2106.04, subsection II.
Regarding independent claim 36, following limitations recite a judicial exception:
“receive first medical information for each of the patients, wherein the medical information includes at least one of the medical events and a time associated with the at least one of the medical events”
[Mental Process] – receiving data can be heard and seen which involves observations, evaluations, judgments, and opinions that is capable of being performed in the human mind with the assistance of paper and pen
“generate a summary of the medical information”
[Mathematical Calculations] – generating a summary of the medical information involves creating a vector to be embedded which requires mathematical computation which recites to an abstract idea
[Mental Process] – generating a summary based on the information is simply collecting and analyzing the information which involves observations, evaluations, judgments, and opinions that is capable of being performed in the human mind with the assistance of paper and pen
“generate a multivariate point process model based on the summarized medical information, wherein each of the medical events has its own distinct sub-model which tracks progression of interevent times for that particular medical event”
[Mental Process] – generating the multivariate point process model, which is simply a model that analyzes multiple events and times on a continuous time line, where each event has its own sub-model that tracks the progression requires continuous tracking of each event over time which involves observations, evaluations, judgments, and opinions that is capable of being performed in the human mind with the assistance of paper and pen
“receive second medical information for the at least particular one of the patients”
[Mental Process] – receiving data can be heard and seen which involves observations, evaluations, judgments, and opinions that is capable of being performed in the human mind with the assistance of paper and pen
“predict and facilitate at least possible one of the medical events and a predicted time of the at least possible one of the medical events for the at least particular one of the patients”
[Mathematical Calculations] – predicting these features requiring use of survival functions and history functions which requires mathematical computation which recites to an abstract idea.
[Mental Process] – using predicted information to facilitate or help a patient involves observations, evaluations, judgments, and opinions that is capable of being performed in the human mind with the assistance of paper and pen
Step 2A Prong 2 – whether the claim recites additional elements that integrate the exception into a practical application of the exception?
Regarding Claim 36, the claim recites additional elements of
“a computer hardware”
A computer hardware is recited at a high level of generality and is merely adding words “apply it” to the judicial exception. (see MPEP 2106.05(f))
[Even when viewed in combination, the additional elements do no more than automate the mental processes that a person could perform, using computer components as a tool, thus the claim as a whole does not integrate into a practical application.]
Step 2B – whether the claim as a whole amount to significantly more than the judicial exception? I.e. Are there any additional elements (features/limitations/step) recited in the claim beyond the abstract idea?
The claim does not provide an inventive concept (significantly more than the abstract idea). The claim is ineligible.
As explained above, the additional element [1] is considered a mere instruction to apply an exception to the generic computer components (see MPEP 2106.05(f)). This limitation remains a mere instruction to apply an exception even upon reconsideration. Even when considered in combination, the additional element represents a mere instruction to apply an exception, which cannot provide an inventive concept.
Regarding Claim 42
Step 1 – whether the claim falls within any statutory category. See MPEP 2016.03
Claim 42 is a dependent claim of 36, thus it falls within the same category of statutory subject matter.
Step 2A Prong 1 – whether the claim recites a judicial exception. See MPEP 2106.04, subsection II.
Regarding dependent claim 42, following limitations recite a judicial exception:
“facilitate or control the treatment of the at least particular one of the patients based on the generated at least possible one of the medical events and the predicted time”
[Mathematical Calculations] – generating these events and times based on the distribution involves use of mathematical functions and calculations which recites to an abstract idea
[Mental Process] – facilitating or controlling the treatment of the patients involves observations, evaluations, judgments, and opinions that is capable of being performed in the human mind with the assistance of paper and pen
Step 2A Prong 2 – whether the claim recites additional elements that integrate the exception into a practical application of the exception?
Regarding Claim 42, the claim recites additional elements of
“the computer hardware”
The computer hardware is recited at a high level of generality and is merely adding words “apply it” to the judicial exception. (see MPEP 2106.05(f))
[Even when viewed in combination, the additional elements do no more than automate the mental processes that a person could perform, using computer components as a tool, thus the claim as a whole does not integrate into a practical application.]
Step 2B – whether the claim as a whole amount to significantly more than the judicial exception? I.e. Are there any additional elements (features/limitations/step) recited in the claim beyond the abstract idea?
The claim does not provide an inventive concept (significantly more than the abstract idea). The claim is ineligible.
As explained above, the additional element [1] is considered a mere instruction to apply an exception to the generic computer components (see MPEP 2106.05(f)). This limitation remains a mere instruction to apply an exception even upon reconsideration. Even when considered in combination, the additional element represents a mere instruction to apply an exception, which cannot provide an inventive concept.
Claim Rejections - 35 USC § 103
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 (i.e., changing from AIA to pre-AIA ) 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 1-5, 7, 15, 29, 35 are rejected under 35 U.S.C. 103 as being unpatentable over by Shchur et al. (Shchur), “Intensity-free learning of temporal point processes”, listed in IDS filed on 08/08/2024, published on 2020, 21 Pages in view of Truccolo et a. (Truccolo), U.S. Patent Application Number 20130261490-A1 listed in IDS filed on 01/19/2024.
As to independent Claim 1,
Shchur teaches a method for predicting medical events used for a treatment of at least particular one of a plurality of patients (Shchur, Pg1, Introduction, Paragraph1, Lines1-3, "Visits to hospitals, purchases in e-commerce systems, financial transactions, posts in social media — various forms of human activity can be represented as discrete events happening at irregular intervals", Pg4, Section3.3, Paragraph3, Lines1-3, “In some scenarios, we might be interested in learning from multiple event sequences. In such case, we can assign each sequence T_j a learnable sequence embedding vector e_j. By optimizing e_j, the model can learn to distinguish between sequences that come from different distributions” and Shchur, Pg7, Paragraph1, Lines1-2, "The task is to predict the time T_i until the next event given the history H_i”, wherein sequence-specific conditioning framework which assigns individual learnable vectors to separate event streams in order to capture user-specific or patient-specific, as mentioned about the hospital visits, latent characteristics. Therefore, it is utilizing the medical information to learn the latent characteristics to predict future events or the medical events, which is equivalent to the claimed invention), comprising:
receiving first medical information for each of the patients, wherein the medical information includes at least one of the medical events and a time associated with the at least one of the medical events (Shchur, Pg1, Introduction, Paragraph1, Lines1-3, "Visits to hospitals, purchases in e-commerce systems, financial transactions, posts in social media — various forms of human activity can be represented as discrete events happening at irregular intervals", Pg1, Background, Definition, Lines1-2, "A temporal point process (TPP) is a random process whose realizations consist of a sequence of strictly increasing arrival times T = {t1, ..., tN}" and Pg14, Subsection D.1, Paragraph2, Lines2-4, "In case we have marks, we additionally input m_i - the index of the mark class from which we get mi mark embedding vector m_i", wherein visiting the hospitals inherently mean there is medical information associated with the visit (hereinafter, will treat the data as this medical information). Also, for each activity, there are associated arrival time T and an event, or the medical event, mi, thus it is functionally equivalent to the claimed invention);
generating a summary of the medical information (Shchur, Pg4, Section 3.3, History, Lines1-4, "A crucial feature of temporal point processes is that the time T_i = (t_i - t_i-1) until the next
event may be influenced by all the events that happened before. A standard way of capturing this dependency is to process the event history H_i with a recurrent neural network (RNN) and embed it
into a fixed-dimensional vector hi in R^H", wherein processing the history H_i and embedding it serves to compact a sequence of past irregular temporal events into a single representative summary vector (the corresponding summary of the medical information) to serve as a conditioning context for subsequent predictive modeling, which is functionally equivalent to the claimed invention of creating one compressed history encoding vector, h_i, which represents the summary of the medical information);
generating a multivariate point process model based on the summarized medical information, wherein a computation of a non-estimated probability distribution is used to train the multivariate point process model (Shchur, Pg2, Paragraph4, section: This work, Lines 2-3, "Instead of modeling the conditional intensity lambda*(t), we suggest to directly learn the conditional distribution p*(T)", Pg3, Paragraph3, Lines1-2, "For both models, we can evaluate the inverse transformations (g1^-1, ..., gM^-1), which means the model can be efficiently trained via maximum likelihood", Pg4, Section 3.3, Obtaining the parameters, Lines2-4, "The history embedding h_i, metadata y_i, and sequence embedding e_j are concatenated into a context vector c_i =[h_i||y_i||e_j]. Then, we obtain the parameters of the distribution p*(T_i) as an affine function of c_i" and Pg5, Section3.4, Paragraph9, Reusability, "If we merge two independent point processes with intensities lambda1(t) and lambda2(t), the merged process has intensity lambda(t) = lambda1(t) + lambda2(t). — An equivalent result exists for the CDFs F1*(T) and F2*(T) of the two independent processes. The CDF of the merged process is obtained as F*(T) = F1*(T) + F2*(T) - F1*(T)F2*(T)", wherein Shchur discloses a method for learning temporal point process by directly modeling the conditional distribution instead of the conditional intensity function by merging two independent processes, which is the corresponding multivariate point process. Shchur further details that because the mathematical transformations can be evaluated analytically, the point process model can be efficiently trained via maximum likelihood in closed form without relying on numerical approximations or Monte Carlo integration. Additionally, the parameters of this point process model are dynamically computed based on a context vector c_i that encapsulates the summarized history embedding h_i. Thus, Shchur's architecture of training an intensity-free point process model is functionally equivalent to the claimed invention);
receiving second medical information for the at least particular one of the patients (Shchur, Pg7, Paragraph1, Lines1-3, "Each dataset consists of multiple sequences of event times. The task is to predict the time T_i until the next event given the history H_i. For each dataset, we use 60% of the sequences for training, 20% for validation and 20% for testing", wherein 20% of the dataset which is used for training includes the medical information as mentioned above, which means this 20% data will be used as an unseen data once the training of the model is finished for the test/live inference purpose, thus it is equivalent to the claimed invention's receiving the second medical information.)
Shchur teaches about predicting at least possible one of the medical events and a predicted time of the at least possible one of the medical events (Shchur, Pg7, Paragraph1, Lines1-3, "Each dataset consists of multiple sequences of event times. The task is to predict the time T_i until the next event given the history H_i. For each dataset, we use 60% of the sequences for training, 20% for validation and 20% for testing" and Pg7, Section5.2, Paragraph1, Lines4-6, "The RNN takes a tuple (T_i, m_i) as input at each time step, where m_i is the mark. Moreover, the loss function now includes a term for predicting the next mark: L(theta) =
PNG
media_image1.png
25
244
media_image1.png
Greyscale
", wherein as mentioned above, the 20% of the unseen dataset will be used for the testing/live inferencing purpose to predict next events based on the history vector. Also, as mentioned above, the data will be medical information such that the loss function will predict the next event, m_i, according to the equation with the associated future time step T_i). However, Shchur does not teach about using this predicted data to facilitate one of the patients. From the same field of endeavor, Truccolo teaches this limitation (Truccolo, Pg3, Paragraph [0030], Lines 1-2, “An embodiment of the method provides treating the subject based on the prediction, detection or diagnosis”)
Shchur and Truccolo are analogous to the claimed invention as they are from the same field of endeavor of predictive medical informatics and real-time clinical decision support workflows. Therefore, it would have been obvious, before the effective filing date, to combine the high-performance, intensity-free neural temporal point process architecture that computes precise non-estimated probability profiles from historical sequence of Shchur with the live patient data-stream receiving interface and proactive early treatment intervention framework of Truccolo. The motivation is as recited by Truccolo (Truccolo, Pg22, Claims28-29, “28. The method according to claim 17 wherein the method further comprises providing a diagnosis based on the prediction or detection. 29. The method according to claim 17, wherein the method further comprises providing a prognosis based on the diagnosis”) such that transitioning Shchur’s advanced predictive model from a static post-hoc evaluation environment to an active clinical deployment phase by adopting the live monitoring and early intervention architecture.
As to dependent Claim 2,
The combination of Shchur and Truccolo teaches, as mentioned above, all the limitations of Claim 1. The combination teaches about the overall blueprint of generating a multivariate point process model that predicts future events and the associated times based on the medical information or the summary of the medical information.
Shchur further teaches the method of claim 1, further comprising
specifying a dependence between the future time and the future event (Shchur, Pg7, Section5.2, Paragraph1, Lines4-6, "The RNN takes a tuple (T_i, m_i) as input at each time step, where m_i is the mark. Moreover, the loss function now includes a term for predicting the next mark: L(theta) =
PNG
media_image1.png
25
244
media_image1.png
Greyscale
, wherein both the future interval time(T_i) and the future event category (m_i) are conditioned upon a shared, common recurrent neural network hidden history vector (h_i) generated from past event-time pairs, thereby establishing an inherent statistical dependence mediated through the common history embedding, which is functionally equivalent to the claimed invention.)
As to dependent Claim 3,
The combination of Shchur and Truccolo teaches, as mentioned above, all the limitations of Claim 1. The combination teaches about the overall blueprint of generating a multivariate point process model that predicts future events and the associated times based on the medical information or the summary of the medical information.
Shchur further teaches the method of claim 1, wherein
the multivariate point process model specifies a conditional probability of each of the medical events (Pg19, F.2, Detailed setup, Lines5-6, "The next mark m_i at time t_i is predicted using a categorical distribution p*(m_i). The distribution is parametrized by the vector pi_i, where pi_i,c is the probability of event m_i = c", wherein Shchur discloses that in the multivariate extension (marked temporal point process), the model explicitly calculates the conditional probability for each incoming event type such that next categorical mark (m_i) is governed by a conditional probability distribution (p*(m_i)) that explicitly assigns a discrete probability value(pi_i,c) to each possible event type given the history, thus it is functionally equivalent to the claimed invention.)
As to dependent Claim 4,
The combination of Shchur and Truccolo teaches, as mentioned above, all the limitations of Claim 3. It teaches about the model explicitly calculates the conditional probability for each incoming event type.
Shchur further teaches the method of claim 3, wherein
the multivariate point process model is based on a survival function and a history function which is associated with the summarized medical information (Shchur, Pg4, Section 3.3, History, Lines2-4, "A standard way of capturing this dependency is to process the event history H_i with a recurrent neural network (RNN) and embed it into a fixed-dimensional vector h_i in R^H" and Pg12, Equation
PNG
media_image2.png
60
423
media_image2.png
Greyscale
, wherein the history function maps directly to the event history function (H_i) encoded into a summarized vector (h_i), and the survival function maps to probability formulation utilizing the survival operator (1 - F*(T_i)) which represents the exact mathematical equivalent of a survival function in point process theory. Instead of relying on the integration of the intensity function of old models that is inherently slow, using the direct computation of survival function to find the likelihood is much faster, thus it is functionally equivalent to the claimed invention.)
As to dependent Claim 5,
The combination of Shchur and Truccolo teaches, as mentioned above, all the limitations of Claim 4. It teaches about the model is based on the survival function and the history function that is associated with the summarized medical information vector, h_i.
Shchur further teaches the method of claim 4, wherein the conditional probability is determined based on the survival function in view of the history function (Shchur, Pg12, Lines9-11, "Given the conditional PDF and CDF, we can compute the conditional intensity lambda*(t) and the cumulative intensity A*(T) for each model as
PNG
media_image3.png
54
220
media_image3.png
Greyscale
", Pg4, Section 3.3, Obtaining the parameters, Lines2-4, "The history embedding h_i, metadata y_i, and sequence embedding e_j are concatenated into a context vector c_i =[h_i||y_i||e_j]. Then, we obtain the parameters of the distribution p*(T_i) as an affine function of c_i" and Pg2, Paragraph4, section: This work, Lines 2-3, "Instead of modeling the conditional intensity lambda*(t), we suggest to directly learn the conditional distribution p*(T)", wherein Shchur explicitly discloses an "intensity-free" temporal point process architecture where the model completely bypasses the traditional parameterization of the conditional intensity function during execution. Under this framework, Shchur establishes the mathematical entity of the conditional probability density (p*) or the corresponding conditional probability and its survival function complement (1 - F*) are natively integrated. Crucially, the parameters defining these density and survival operators are directly obtained as an affine function of c_i which contains the recurrent history embedding function h_i, thus it is functionally equivalent to the claimed invention.)
As to dependent Claim 7,
The combination of Shchur and Truccolo teaches, as mentioned above, all the limitations of Claim 1. The combination teaches about the overall blueprint of generating a multivariate point process model that predicts future events and the associated times based on the medical information or the summary of the medical information.
The combination further teaches the method of claim 1, further comprising
facilitating or controlling the treatment of the at least particular one of the patients based on the generated at least possible one of the medical events and the predicted time (Shchur, Pg7, Paragraph1, Lines1-3, "Each dataset consists of multiple sequences of event times. The task is to predict the time T_i until the next event given the history H_i. For each dataset, we use 60% of the sequences for training, 20% for validation and 20% for testing" and Pg7, Section5.2, Paragraph1, Lines4-6, "The RNN takes a tuple (T_i, m_i) as input at each time step, where m_i is the mark. Moreover, the loss function now includes a term for predicting the next mark: L(theta) =
PNG
media_image1.png
25
244
media_image1.png
Greyscale
" and Truccolo, Pg3, Paragraph [0030], Lines 1-2, “An embodiment of the method provides treating the subject based on the prediction, detection or diagnosis”, wherein as mentioned in Claim1, Shchur predicts the future events and the associated time while Truccolo uses such predicted data to facilitate or control the treatment of the patients, which is functionally equivalent to the claimed invention.)
As to independent Claim 15,
it is a non-transitory computer readable medium claim that contains similar limitations of Claim 1 and thus rejected under the same rationale.
As to independent Claim 29,
it is a system claim that contains similar limitations of Claim 1 and thus rejected under the same rationale.
As to dependent Claim 35,
it is a system claim that contains similar limitations of Claim 7 and thus rejected under the same rationale.
Claims 6, 8-14, 22, 36, 42 are rejected under 35 U.S.C. 103 as being unpatentable over by Shchur and Truccolo as mentioned in Claim 1 in further view of Tsiatis et al. (Tsiatis), “A nonidentifiability aspect of the problem of competing risks”, Non-Patent Literature listed in IDS filed on 08/08/2024, published on 1975, 3Pages.
As to dependent Claim 6,
The combination of Shchur and Truccolo teaches, as mentioned above, all the limitations of Claim 1. The combination teaches about the overall blueprint of generating a multivariate point process model that predicts future events and the associated times based on the medical information or the summary of the medical information.
As mentioned above in Claim 1, Shchur discloses the mathematical paradigm for merging independent point processes and modeling multivariate event streams (Shchur, Pg5, Section3.4, Paragraph9, Reusability, "If we merge two independent point processes with intensities lambda1(t) and lambda2(t), the merged process has intensity lambda(t) = lambda1(t) + lambda2(t). — An equivalent result exists for the CDFs F1*(T) and F2*(T) of the two independent processes. The CDF of the merged process is obtained as F*(T) = F1*(T) + F2*(T) - F1*(T)F2*(T)").
However, Shchur does not teach about the multivariate point process model facilitates a generation of the at least possible one of the medical events and the predicted time based on a sample from all of event distributions. In the same field of endeavor, Tsiatis teaches this limitation (Tsiatis, Pg20, Left Column, Paragraph1, Lines3-6 and Lines12-15, "Consider an individual living organism born at time t = 0, and assume that through its lifetime it is exposed to k > 1 different "risks" or possible causes of death R1, R2, ..., Rk. …. The potential survival times Y_i are contrasted with the actual survival time, say X, when the individual in question is exposed to all the k > 1 competing risks, so that X = min(Y1, Y2, ..., Yk)", wherein the foundational formulation for modeling competing risks among multiple potential outcomes explicitly teaching that R1 to Rk are the possible risks and defining that the actual single observed survival event time X is governed by the absolute minimum of all potential component durations so that X = min(Y1,..., Yk). Thus, drawing independent time-to-event samples from each constituent risk distribution (Y1,.., Yk) and computationally select the minimum value to generate the next timeline entry (X) is functionally equivalent to the claimed invention.)
Shchur, Truccolo and Tsiatis are analogous to the claimed invention as they are from the same field of endeavor of stochastic modeling and predictive analytics of multivariate temporal event streams under competing risks. Therefore, it would have been obvious, before the effective filing date, to combine the intensity-free neural temporal point process architecture that models conditional cumulative distribution functions and handles merged independent processes of Shchur and the live patient data-stream receiving interface and proactive early treatment intervention framework of Truccolo with the parallel latent potential survival times framework and the minimum selection operator formulation of Tsiatis. The motivation is as recited by Tsiatis (Tsiatis, Pg20, Left Column, Paragraph2, Lines4-7, "The purpose of such studies is to estimate the net survival probabilities and to predict the patterns of mortality to be expected in hypothetical conditions when certain causes of death are either eliminated or modified in their importance") such that expanding Shchur's merged distribution framework to explicitly execute a minimum-value draw (min(Yi)) across independent latent risk sub-models as taught by Tsiatis, it is possible to simulate forward and accurately predict how the specific modification, elimination, or shifting prominence of one individual clinical event track dynamically alters the patient's overarching sequential treatment timeline and net survival outcomes over a longitudinal period.
As to independent Claim 8,
Shchur teaches a method for predicting medical events used for a treatment of at least particular one of a plurality of patients (Shchur, Pg1, Introduction, Paragraph1, Lines1-3, "Visits to hospitals, purchases in e-commerce systems, financial transactions, posts in social media — various forms of human activity can be represented as discrete events happening at irregular intervals", Pg4, Section3.3, Paragraph3, Lines1-3, “In some scenarios, we might be interested in learning from multiple event sequences. In such case, we can assign each sequence T_j a learnable sequence embedding vector e_j. By optimizing e_j, the model can learn to distinguish between sequences that come from different distributions” and Shchur, Pg7, Paragraph1, Lines1-2, "The task is to predict the time T_i until the next event given the history H_i”, wherein sequence-specific conditioning framework which assigns individual learnable vectors to separate event streams in order to capture user-specific or patient-specific, as mentioned about the hospital visits, latent characteristics. Therefore, it is utilizing the medical information to learn the latent characteristics to predict future events or the medical events, which is equivalent to the claimed invention), comprising:
receiving first medical information for each of the patients, wherein the medical information includes at least one of the medical events and a time associated with the at least one of the medical events (Shchur, Pg1, Introduction, Paragraph1, Lines1-3, "Visits to hospitals, purchases in e-commerce systems, financial transactions, posts in social media — various forms of human activity can be represented as discrete events happening at irregular intervals", Pg1, Background, Definition, Lines1-2, "A temporal point process (TPP) is a random process whose realizations consist of a sequence of strictly increasing arrival times T = {t1, ..., tN}" and Pg14, Subsection D.1, Paragraph2, Lines2-4, "In case we have marks, we additionally input m_i - the index of the mark class from which we get mi mark embedding vector m_i", wherein visiting the hospitals inherently mean there is medical information associated with the visit (hereinafter, will treat the data as this medical information). Also, for each activity, there are associated arrival time T and an event, or the medical event, mi, thus it is functionally equivalent to the claimed invention);
generating a summary of the medical information (Shchur, Pg4, Section 3.3, History, Lines1-4, "A crucial feature of temporal point processes is that the time T_i = (t_i - t_i-1) until the next
event may be influenced by all the events that happened before. A standard way of capturing this dependency is to process the event history H_i with a recurrent neural network (RNN) and embed it
into a fixed-dimensional vector hi in R^H", wherein processing the history H_i and embedding it inherently compact a sequence of past irregular temporal events into a single representative summary vector to serve as a conditioning context for subsequent predictive modeling which is functionally equivalent to the claimed invention);
receiving second medical information for the at least particular one of the patients (Shchur, Pg7, Paragraph1, Lines1-3, "Each dataset consists of multiple sequences of event times. The task is to predict the time T_i until the next event given the history H_i. For each dataset, we use 60% of the sequences for training, 20% for validation and 20% for testing", wherein 20% of the dataset which is used for training includes the medical information as mentioned above, which means this 20% data will be used as an unseen data once the training of the model is finished for the test/live inference purpose, thus it is equivalent to the claimed invention's receiving the second medical information.)
Shchur teaches about predicting at least possible one of the medical events and a predicted time of the at least possible one of the medical events (Shchur, Pg7, Paragraph1, Lines1-3, "Each dataset consists of multiple sequences of event times. The task is to predict the time T_i until the next event given the history H_i. For each dataset, we use 60% of the sequences for training, 20% for validation and 20% for testing" and Pg7, Section5.2, Paragraph1, Lines4-6, "The RNN takes a tuple (T_i, m_i) as input at each time step, where m_i is the mark. Moreover, the loss function now includes a term for predicting the next mark: L(theta) =
PNG
media_image1.png
25
244
media_image1.png
Greyscale
", wherein as mentioned above, the 20% of the unseen dataset will be used for the testing/live inferencing purpose to predict next events based on the history vector. Also, as mentioned above, the data will be medical information such that the loss function will predict the next event, m_i, according to the equation with the associated future time step T_i) However, Shchur does not teach about using this predicted data to facilitate one of the patients. From the same field of endeavor, Truccolo teaches this limitation (Truccolo, Pg3, Paragraph [0030], Lines 1-2, “An embodiment of the method provides treating the subject based on the prediction, detection or diagnosis”)
Shchur and Truccolo are analogous to the claimed invention as they are from the same field of endeavor of predictive medical informatics and real-time clinical decision support workflows. Therefore, it would have been obvious, before the effective filing date, to combine the high-performance, intensity-free neural temporal point process architecture that computes precise non-estimated probability profiles from historical sequence of Shchur with the live patient data-stream receiving interface and proactive early treatment intervention framework of Truccolo. The motivation is as recited by Truccolo (Truccolo, Pg22, Claims28-29, “28. The method according to claim 17 wherein the method further comprises providing a diagnosis based on the prediction or detection. 29. The method according to claim 17, wherein the method further comprises providing a prognosis based on the diagnosis”) such that transitioning Shchur’s advanced predictive model from a static post-hoc evaluation environment to an active clinical deployment phase by adopting the live monitoring and early intervention architecture.
Shchur teaches about generating a multivariate point process model parameterized by sequential history summaries, and recognizes the mathematical validity of analyzing multivariate systems by treating them as a combination of separate, independent constituent event process curves as mentioned in Claim1 (Shchur, Pg4, Section 3.3, Obtaining the parameters, Lines2-4, "The history embedding h_i, metadata y_i, and sequence embedding e_j are concatenated into a context vector c_i =[h_i||y_i||e_j]. Then, we obtain the parameters of the distribution p*(T_i) as an affine function of c_i", Shchur, Pg5, Section3.4, Paragraph9, Reusability, "If we merge two independent point processes with intensities lambda1(t) and lambda2(t), the merged process has intensity lambda(t) = lambda1(t) + lambda2(t). — An equivalent result exists for the CDFs F1*(T) and F2*(T) of the two independent processes. The CDF of the merged process is obtained as F*(T) = F1*(T) + F2*(T) - F1*(T)F2*(T)".) However, Shchur does not teach wherein teach of the medical events has its own distinct sub-model which tracks progression of interevent times for that particular medical event. In the same field of endeavor, Tsiatis teaches this limitation (Tsiatis, Pg20, Left Column, Paragraph1, Lines3-9, "Consider an individual living organism born at time t = 0, and assume that through its lifetime it is exposed to k > 1 different "risks" or possible causes of death R1, R2, ..., Rk For i = 1,2, ..., k let Y_i denote a random variable described as the 'potential survival time' of the individual in hypothetical conditions in which R_i is the only risk of death, and let H_i(t) = P{Y_i > t}.
Tsiatis, Pg21, Left Column, Equation8, "In particular, if the potential survival times are mutually independent, so that
PNG
media_image4.png
45
277
media_image4.png
Greyscale
", wherein each individual risk or cause R_i within a multivariate stream is formalized via its own distinct, isolated temporal probability matrix with respective Y_i, which is equivalent to the claimed invention.)
Shchur, Truccolo and Tsiatis are analogous to the claimed invention as they are from the same field of endeavor of stochastic modeling and predictive analytics of multivariate temporal event streams under competing risks. Therefore, it would have been obvious, before the effective filing date, to combine the intensity-free neural temporal point process architecture that models conditional cumulative distribution functions and handles merged independent processes of Shchur and the live patient data-stream receiving interface and proactive early treatment intervention framework of Truccolo with the parallel latent potential survival times framework and the minimum selection operator formulation of Tsiatis. The motivation is as recited by Tsiatis (Tsiatis, Pg20, Left Column, Paragraph2, Lines4-7, "The purpose of such studies is to estimate the net survival probabilities and to predict the patterns of mortality to be expected in hypothetical conditions when certain causes of death are either eliminated or modified in their importance") such that expanding Shchur's merged distribution framework to explicitly execute a minimum-value draw (min(Yi)) across independent latent risk sub-models as taught by Tsiatis, it is possible to simulate forward and accurately predict how the specific modification, elimination, or shifting prominence of one individual clinical event track dynamically alters the patient's overarching sequential treatment timeline and net survival outcomes over a longitudinal period.
As to dependent Claim 9,
The combination of Shchur, Truccolo and Tsiatis teaches, as mentioned above, all the limitations of Claim 8. The combination teaches about the overall blueprint of generating a multivariate point process model that predicts future events and the associated times based on the medical information or the summary of the medical information.
Shchur further teaches the method of claim 8, further comprising
specifying a dependence between the future time and the future event (Shchur, Pg7, Section5.2, Paragraph1, Lines4-6, "The RNN takes a tuple (T_i, m_i) as input at each time step, where m_i is the mark. Moreover, the loss function now includes a term for predicting the next mark: L(theta) =
PNG
media_image1.png
25
244
media_image1.png
Greyscale
, wherein both the future interval time(T_i) and the future event category (m_i) are conditioned upon a shared, common recurrent neural network hidden history vector (h_i) generated from past event-time pairs, thereby establishing an inherent statistical dependence mediated through the common history embedding, which is functionally equivalent to the claimed invention.)
As to dependent Claim 10,
The combination of Shchur, Truccolo and Tsiatis teaches, as mentioned above, all the limitations of Claim 8. The combination teaches about the overall blueprint of generating a multivariate point process model that predicts future events and the associated times based on the medical information or the summary of the medical information.
Shchur further teaches the method of claim 8, wherein
the multivariate point process model specifies a conditional probability of each of the medical events (Pg19, F.2, Detailed setup, Lines5-6, "The next mark m_i at time t_i is predicted using a categorical distribution p*(m_i). The distribution is parametrized by the vector pi_i, where pi_i,c is the probability of event m_i = c", wherein Shchur discloses that in the multivariate extension (marked temporal point process), the model explicitly calculates the conditional probability for each incoming event type such that next categorical mark (m_i) is governed by a conditional probability distribution (p*(m_i)) that explicitly assigns a discrete probability value(pi_i,c) to each possible event type given the history, thus it is functionally equivalent to the claimed invention.)
As to dependent Claim 11,
The combination of Shchur, Truccolo and Tsiatis teaches, as mentioned above, all the limitations of Claim 10. It teaches about the model explicitly calculates the conditional probability for each incoming event type.
Shchur further teaches the method of claim 10, wherein
the multivariate point process model is based on a survival function and a history function which is associated with the summarized medical information (Shchur, Pg4, Section 3.3, History, Lines2-4, "A standard way of capturing this dependency is to process the event history H_i with a recurrent neural network (RNN) and embed it into a fixed-dimensional vector h_i in R^H" and Pg12, Equation
PNG
media_image2.png
60
423
media_image2.png
Greyscale
, wherein the history function maps directly to the event history function (H_i) encoded into a summarized vector (h_i), and the survival function maps to probability formulation utilizing the survival operator (1 - F*(T_i)) which represents the exact mathematical equivalent of a survival function in point process theory. Instead of relying on the integration of the intensity function of old models that is inherently slow, using the direct computation of survival function to find the likelihood is much faster, thus it is functionally equivalent to the claimed invention.)
As to dependent Claim 12,
The combination of Shchur, Truccolo and Tsiatis teaches, as mentioned above, all the limitations of Claim 4. It teaches about the model is based on the survival function and the history function that is associated with the summarized medical information vector, h_i.
Shchur further teaches the method of claim 11, wherein the conditional probability is determined based on the survival function in view of the history function (Shchur, Pg12, Lines9-11, "Given the conditional PDF and CDF, we can compute the conditional intensity lambda*(t) and the cumulative intensity A*(T) for each model as
PNG
media_image3.png
54
220
media_image3.png
Greyscale
", Pg4, Section 3.3, Obtaining the parameters, Lines2-4, "The history embedding h_i, metadata y_i, and sequence embedding e_j are concatenated into a context vector c_i =[h_i||y_i||e_j]. Then, we obtain the parameters of the distribution p*(T_i) as an affine function of c_i" and Pg2, Paragraph4, section: This work, Lines 2-3, "Instead of modeling the conditional intensity lambda*(t), we suggest to directly learn the conditional distribution p*(T)", wherein Shchur explicitly discloses an "intensity-free" temporal point process architecture where the model completely bypasses the traditional parameterization of the conditional intensity function during execution. Under this framework, Shchur establishes the mathematical entity of the conditional probability density (p*) or the corresponding conditional probability and its survival function complement (1 - F*) are natively integrated. Crucially, the parameters defining these density and survival operators are directly obtained as an affine function of c_i which contains the recurrent history embedding function h_i, thus it is functionally equivalent to the claimed invention.)
As to dependent Claim 13,
The combination of Shchur, Truccolo and Tsiatis teaches, as mentioned above, all the limitations of Claim 8. The combination teaches about the overall blueprint of generating a multivariate point process model that predicts future events and the associated times based on the medical information or the summary of the medical information.
As mentioned above in Claim 8, Shchur discloses the mathematical paradigm for merging independent point processes and modeling multivariate event streams (Shchur, Pg5, Section3.4, Paragraph9, Reusability, "If we merge two independent point processes with intensities lambda1(t) and lambda2(t), the merged process has intensity lambda(t) = lambda1(t) + lambda2(t). — An equivalent result exists for the CDFs F1*(T) and F2*(T) of the two independent processes. The CDF of the merged process is obtained as F*(T) = F1*(T) + F2*(T) - F1*(T)F2*(T)").
However, Shchur does not teach about the multivariate point process model facilitates a generation of the at least possible one of the medical events and the predicted time based on a sample from all of event distributions. In the same field of endeavor, Tsiatis teaches this limitation (Tsiatis, Pg20, Left Column, Paragraph1, Lines3-6 and Lines12-15, "Consider an individual living organism born at time t = 0, and assume that through its lifetime it is exposed to k > 1 different "risks" or possible causes of death R1, R2, ..., Rk. …. The potential survival times Y_i are contrasted with the actual survival time, say X, when the individual in question is exposed to all the k > 1 competing risks, so that X = min(Y1, Y2, ..., Yk)", wherein the foundational formulation for modeling competing risks among multiple potential outcomes explicitly teaching that R1 to Rk are the possible risks and defining that the actual single observed survival event time X is governed by the absolute minimum of all potential component durations so that X = min(Y1,..., Yk). Thus, drawing independent time-to-event samples from each constituent risk distribution (Y1,.., Yk) and computationally select the minimum value to generate the next timeline entry (X) is functionally equivalent to the claimed invention.)
Shchur, Truccolo and Tsiatis are analogous to the claimed invention as they are from the same field of endeavor of stochastic modeling and predictive analytics of multivariate temporal event streams under competing risks. Therefore, it would have been obvious, before the effective filing date, to combine the intensity-free neural temporal point process architecture that models conditional cumulative distribution functions and handles merged independent processes of Shchur and the live patient data-stream receiving interface and proactive early treatment intervention framework of Truccolo with the parallel latent potential survival times framework and the minimum selection operator formulation of Tsiatis. The motivation is as recited by Tsiatis (Tsiatis, Pg20, Left Column, Paragraph2, Lines4-7, "The purpose of such studies is to estimate the net survival probabilities and to predict the patterns of mortality to be expected in hypothetical conditions when certain causes of death are either eliminated or modified in their importance") such that expanding Shchur's merged distribution framework to explicitly execute a minimum-value draw (min(Yi)) across independent latent risk sub-models as taught by Tsiatis, it is possible to simulate forward and accurately predict how the specific modification, elimination, or shifting prominence of one individual clinical event track dynamically alters the patient's overarching sequential treatment timeline and net survival outcomes over a longitudinal period.
As to dependent Claim 14,
The combination of Shchur, Truccolo and Tsiatis teaches, as mentioned above, all the limitations of Claim 8. The combination teaches about the overall blueprint of generating a multivariate point process model that predicts future events and the associated times based on the medical information or the summary of the medical information.
The combination further teaches the method of claim 1, further comprising
facilitating or controlling the treatment of the at least particular one of the patients based on the generated at least possible one of the medical events and the predicted time (Shchur, Pg7, Paragraph1, Lines1-3, "Each dataset consists of multiple sequences of event times. The task is to predict the time T_i until the next event given the history H_i. For each dataset, we use 60% of the sequences for training, 20% for validation and 20% for testing" and Pg7, Section5.2, Paragraph1, Lines4-6, "The RNN takes a tuple (T_i, m_i) as input at each time step, where m_i is the mark. Moreover, the loss function now includes a term for predicting the next mark: L(theta) =
PNG
media_image1.png
25
244
media_image1.png
Greyscale
" and Truccolo, Pg3, Paragraph [0030], Lines 1-2, “An embodiment of the method provides treating the subject based on the prediction, detection or diagnosis”, wherein as mentioned in Claim8, Shchur predicts the future events and the associated time while Truccolo uses such predicted data to facilitate or control the treatment of the patients, which is functionally equivalent to the claimed invention.)
As to independent Claim 22,
it is a non-transitory computer readable medium claim that contains similar limitations of Claim 8 and thus rejected under the same rationale.
As to independent Claim 36,
it is a system claim that contains similar limitations of Claim 8 and thus rejected under the same rationale.
As to dependent Claim 42,
it is a system claim that contains similar limitations of Claim 14 and thus rejected under the same rationale.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Mehrasa et al., U.S Patent Application Number 20200160176-A1
Saria et al., U.S Patent Application Number 20200005941-A1
Guo et al., U.S Patent Application Number 20200019840-A1
Truccolo et al., U.S Patent Application Number 10448877-B2
Shchur et al., "Neural Temporal Point Processes: A Review", Published on May 2021, arXiv, V4, 9 Pages
Mozer, "Discrete-Event Continuous-Time Recurrent Nets", Published on Oct 2017, arXiv, V1, 21 Pages
Bahadori, "Temporal-Clustering Invariance in Irregular Healthcare Time Series", Published on Apr 2019, V1, 16 Pages
Zhu, "Dynamic prediction of time to event with survival curves", Published on March 2021, V2, arXiv, 11 Pages
Any inquiry concerning this communication or earlier communications from the examiner should be directed to DONG YOON JUNG whose telephone number is (571)270-0198. The examiner can normally be reached 8am-5pm.
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, Cesar Paula can be reached at (571) 272-4128. 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.
/DONG YOON JUNG/Examiner, Art Unit 2145
/CHAU T NGUYEN/Primary Examiner, Art Unit 2145
Prosecution Insights