DETAILED ACTION
The present office action represents a nonfinal action on the merits.
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
This application claims the priority date of a foreign application EP21185957.4 dated July 15, 2021 and 371 of PCT/EP2022/069799 dated July 14, 2022.
Status of Claims
Claims 1, 3, 5-6, 8-10, 14, and 18-20 are amended, claim 21 is cancelled, and claims 1-20 are 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 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more.
Claims 1-15 are drawn to a computer-implemented method of predicting at least one future point on a pharmacokinetic curve for a given species, which is within the four statutory categories (i.e., process). Claims 16-20 are drawn to a computer-implemented method of generating a machine learning model for predicting at least one future point on a pharmacokinetic curve for a given species, which is within the four statutory categories (i.e., process).
Claims 1-15 recite a computer-implemented method of predicting at least one future point on a pharmacokinetic curve for a given species, the computer-implemented method including:
receiving an input comprising data representing a sequence of concentration-time points of a pharmacokinetic curve, each concentration-time point indicative of an amount of the given species in a subject's body at a respective time; and
applying a machine learning model to the input data, the machine learning model configured to generate an output comprising at least one subsequent concentration-time point in the pharmacokinetic curve.
Claims 16-20 recite computer-implemented method of generating a machine learning model for predicting at least one future point on a pharmacokinetic curve for a given species, the computer- implemented method comprising:
providing a machine learning algorithm;
receiving training data, the training data comprising a plurality of pharmacokinetic curves; and
training the machine learning algorithm using the received training data, thereby generating the machine learning model.
The bolded limitations, given the broadest reasonable interpretation, cover a certain method of organizing human activity and mathematical concepts, but for the recitation of generic computer components. The underlined limitations are not part of the identified abstract idea (the method of organizing human activity or mathematical concepts) and are deemed “additional elements,” and will be discussed in further detail below.
Dependent claims 2-15 and 17-20 are similarly rejected because they either further define/narrow the abstract idea and/or do not further limit the claim to a practical application or provide an inventive concept such that the claims are subject matter eligible even when considered individually or as an ordered combination.
The dependent claims include additional limitations but these only serve to further limit the abstract idea, and hence are nonetheless directed towards fundamentally the same abstract idea as independent claims 1 and 16.
The dependent claims do not contain additional elements.
Claims 1-20 are not integrated into a practical application because there are no additional elements (i.e., the limitations not identified as part of the abstract idea).
Dependent claims 2-15 and 17-20 include other limitations, but none of these functions are deemed significantly more than the abstract idea.
Looking at the limitations as an ordered combination adds nothing that is not already present when looking at the elements taken individually, and there is no indication that the combination of elements improves the prediction of pharmacokinetic curves.
Therefore, whether taken individually or as an ordered combination, claims 1-20 are nonetheless rejected under 35 U.S.C. 101 as being directed to non-statutory subject matter.
Claim Rejections - 35 USC § 102
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 the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 1-2 and 10 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Tang (U.S. Pub. No. 2020/0311527 A1).
Regarding claim 1, Tang discloses a computer-implemented method of predicting at least one future point on a pharmacokinetic curve for a given species, the computer-implemented method including (Paragraph [0008] discusses pharmacokinetic modeling, generate one or more time series predictions include concentration values of a drug in plasma as a function of time following administration of a dose of the drug.):
receiving an input comprising data representing a sequence of concentration-time points of a pharmacokinetic curve, each concentration-time point indicative of an amount of the given species in a subject's body at a respective time (Paragraphs [0011], [0022]-[0024] discuss data pertaining to patient baseline characteristics are provided to the MLP, and data pertaining to the dose level of a drug given to a patient at sequential points in time is provided to the RNN and the output combined to generate a Pk curve showing the relationship between the concentration of a drug in the plasma of a patient and the time after a single dose of the drug has been administered to a patient.); and
applying a machine learning model to the input data, the machine learning model configured to generate an output comprising at least one subsequent concentration-time point in the pharmacokinetic curve (Paragraph [0024] discusses data pertaining to patient baseline characteristics are provided to the MLP, and data pertaining to the dose level of a drug given to a patient at sequential points in time is provided to the RNN. The output of the MLP can be used as the initial state of the RNN. The output of the RNN and the MLP can also be combined to generate a Pk curve showing the relationship between the concentration of a drug in the plasma of a patient and the time after a single dose of the drug has been administered to a patient.).
Regarding claim 2, Tang discloses wherein:
the subsequent concentration-time point of the output is the next concentration-time point after the sequence of concentration-time points forming the input (Paragraph [0008] discusses time series predictions can include concentration values of a drug in plasma as a function of time following administration of a dose of the drug.).
Regarding claim 10, Tang discloses wherein:
the computer-implemented method comprises receiving a plurality of inputs, each input corresponding to a respective dosing regimen and the machine learning model is configured to generate a plurality of outputs, each corresponding to a respective input (Paragraphs [0041] discuss the RSNN includes an MLP and a hidden RNN layer, the Hidden RNN layer receives a first sequential input, and uses the MLP output to process the first sequential input to generate a first RNN output, the hidden RNN layer then receives a second sequential input and uses the first RNN output to process the second sequential input and generate a second RNN output, the hidden RNN layer then receives a third sequential input and uses the second RNN output to process the third sequential input to generate a third RNN output, the MLP output is then added to the third RNN output to generate a time series prediction, the sequential inputs correspond to cumulative amounts of drug injected at a given time.); and
determining a dosing regimen based on the generated plurality of outputs, each comprising at least one subsequent concentration-time point (Paragraphs [0005] and [0008] discuss the MLP and RNN unit are collectively configured to generate one or more time series predictions based at least partially on the RNN output and the MLP output, the predictions can include concentration values of a drug in plasma as a function of time following administration of a dose of the drug.).
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 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.
Claims 3-9 and 11-12 are rejected under 35 U.S.C. 103 as being unpatentable over Tang in view of Mould (U.S. Pub. No. 2019/0326002 A1).
Regarding claim 3, Tang discloses wherein:
the machine learning model comprises:
a curve model comprising a curve network, which is an artificial neural network configured to output one or more subsequent concentration-time points which would be expected in the absence of an administration of a dose of the given species (Paragraph [0024] discusses the residual semi-recurrent neural network includes a multilayer perceptron (MLP) for receiving and processing time invariant data, if being used for Pk modeling, the data pertaining to patient baseline characteristics are provided to the MLP, and data pertaining to the dose level of a drug given to a patient at sequential points in time is provided to the RNN, the output of the RNN and the MLP can also be combined to generate a Pk curve showing the relationship between the concentration of a drug in the plasma of a patient and the time after a single dose of the drug has been administered to a patient.); and
a dose model comprising a dose network, which is an artificial neural network configured to output one or more values indicative of a concentration of the given species after a dose has been administered (Paragraphs [0011], [0024] and [0035] discuss provides residual semi-recurrent neural networks configured to process both time invariant data and time variant data in an efficient manner that improves prediction accuracy, the MLP output can result from processing input data associated with patient baseline characteristics, and the time invariant data can be a sequence of cumulative amounts of a drug injected into a patient, the output of the RNN unit (the time series prediction) can be a Pk curve and the one or more time series predictions can include concentration values of a drug in plasma as a function of time following administration of a dose of the drug.); and
the input further comprises dosage data including at least one value of a dose to be administered (Paragraph [0024] discusses receiving and processing time invariant data and the output of the RNN and the MLP can also be combined to generate a Pk curve showing the relationship between the concentration of a drug in the plasma of a patient and the time after a single dose of the drug has been administered to a patient.).
Tang does not explicitly disclose:
one or more values indicative of an increase in concentration of the given species after a dose has been administered.
Mould teaches:
one or more values indicative of an increase in concentration of the given species after a dose has been administered (Paragraphs [0083]-[0084], [0087] and FIG. 13 discuss dosing regimen includes recommended times and doses to administer one or more pharmaceutical or drugs to the patient, includes increased concentrations and times.).
Therefore, it would have been obvious to one of ordinary skill in the art to modify Tang to include, one or more values indicative of an increase in concentration of the given species after a dose has been administered, as taught by Mould, in order to provide ways to quickly adjust a dosing regimen recommendation for a specific patient, in order to react to fast changes in the patient's medical condition. (Mould Abstract.).
Regarding claim 4, Tang discloses wherein:
the dosage data comprises an absolute dosage value of an initial dosing event, and the times and respective dosage values for at least one subsequent dosing event (Paragraph [0024] discusses provide data pertaining to the dose level of a drug given to a patient at sequential points in time.); and
the dose network is configured to predict the resulting increase in concentration as a result of each of the dosing events described in the dosage data (Paragraph [0008] discuss one or more time series predictions can include concentration values of a drug in plasma as a function of time following administration of a dose of the drug.).
Regarding claim 5, Tang discloses wherein:
the curve network comprises (Paragraph [0024] discusses neural networks and the RNN and the MLP can also be combined to generate a Pk curve.):
at least one long short-term memory, LSTM, layer configured to decompose the sequence of concentration-time points forming the input into parameters representative of the sequence (Paragraphs [0006], [0024], [0035] and FIG. 3 discuss the RNN unit can include a long short-term memory RNN unit, data pertaining to the dose level of a drug given to a patient at sequential points in time is provided to the RNN to sequentially process the received time variant data.); and
at least one densely connected layer configured to combine the parameters in a nonlinear manner in order to predict the at least one subsequent concentration-time point (Paragraphs [0008] and [0055] discuss neural network can be configured to combine the MPL output with the RNN output to generate a residual output. The one or more time series predictions can include concentration values of a drug in plasma as a function of time following administration of a dose of the drug, the RSNN was able to capture the complex nonlinear relationship between the PK values and the cumulative amounts of drug injected, as well as the baseline characteristics.).
Regarding claim 6, Tang discloses wherein:
the dose network comprises (Paragraph [0005] discusses a neural network):
a sequence sub-network configured to receive and process the portion of the input data comprising the sequence of concentration-time points (Paragraphs [0005] and [0034]-[0035] discuss recurrent neural network unit can also receive time invariant input, and process the time invariant input with the time invariant input to generate an output, processing input data associated with patient baseline characteristics, and the time invariant data can be a sequence of cumulative amounts of a drug injected into a patient.); and
a dosage sub-network configured to receive and process the portion of the input data comprising the dosage data (Paragraphs [0034]-[0035] discuss a RNN and processing input data associated with patient baseline characteristics, and the time invariant data can be a sequence of cumulative amounts of a drug injected into a patient.); and
each of the sequence sub-network and the dosage sub-network comprise:
at least one long short-term memory, LSTM, layer configured to decompose a received input into one or more parameters representative of the sequence (Paragraphs [0006], [0024], [0035] and FIG. 3 discuss the RNN unit can include a long short-term memory RNN unit, data pertaining to the dose level of a drug given to a patient at sequential points in time is provided to the RNN to sequentially process the received time variant data.); and
at least one densely connected layer configured to combine the parameters in a nonlinear manner in order to predict the at least one subsequent concentration-time point (Paragraphs [0008] and [0055] discuss neural network can be configured to combine the MPL output with the RNN output to generate a residual output. The one or more time series predictions can include concentration values of a drug in plasma as a function of time following administration of a dose of the drug, the RSNN was able to capture the complex nonlinear relationship between the PK values and the cumulative amounts of drug injected, as well as the baseline characteristics.).
Regarding claim 7, Tang discloses wherein:
the dose network further comprises a combination sub-network which is configured to combine the outputs from the dosage sub-network and the sequence sub-network and to output a parameter indicative of the concentration of the given species as a result of the administration of a dosage or plurality of doses, as described by the dosage data (Paragraphs [0008]-[0011] discuss residual semi-recurrent neural networks (RSNN) receive both time invariant input and time variant input data to generate one or more time series predictions; outputs of the multilayer perceptron and the recurrent neural network unit can be combined to generate the one or more time series predictions of concentration values of a drug in plasma as a function of time following administration of a dose of the drug, a residual output.).
Tang does not explicitly disclose:
indicative of the increase in concentration of the given species as a result of the administration of a dosage or plurality of doses, as described by the dosage data.
Mould teaches:
indicative of the increase in concentration of the given species as a result of the administration of a dosage or plurality of doses, as described by the dosage data (Paragraphs [0083]-[0084], [0087] and FIG. 13 discuss dosing regimen includes recommended times and doses to administer one or more pharmaceutical or drugs to the patient, includes increased concentrations and times.).
Therefore, it would have been obvious to one of ordinary skill in the art to modify Tang to include, indicative of the increase in concentration of the given species as a result of the administration of a dosage or plurality of doses, as described by the dosage data, as taught by Mould, in order to provide ways to quickly adjust a dosing regimen recommendation for a specific patient, in order to react to fast changes in the patient's medical condition. (Mould Abstract.).
Regarding claim 8, Tang discloses further comprising:
adding the output of the dose model to the output of the curve network in order to determine a value for the subsequent concentration-time point (Paragraph [0011] discusses combining the MPL output with the RNN output to generate a residual output; the one or more time series predictions can include concentration values of a drug in plasma as a function of time following administration of a dose of the drug.).
Regarding claim 9, Tang discloses wherein:
applying the machine learning model comprises (Paragraph [0030] discusses applying or processing using the neural network.):
(a) applying the curve network to the initial input data to generate a subsequent concentration-time point (Paragraphs [0024] and [0030] discuss residual semi-recurrent neural network includes a multilayer perceptron (MLP) for receiving and processing time invariant data. The residual semi-recurrent neural network also includes an RNN unit for processing time variant data and The output of the RNN and the MLP can also be combined to generate a Pk curve showing the relationship between the concentration of a drug in the plasma of a patient and the time after a single dose of the drug has been administered to a patient.).
Tang does not explicitly disclose:
(b) applying the curve network to update input data, the updated input data comprising the initial input data and all subsequently-generated concentration-time points; and
(c) repeating step (b).
Mould teaches:
(b) applying the curve network to update input data, the updated input data comprising the initial input data and all subsequently-generated concentration-time points (Paragraphs [0005]-[0006] discuss when additional data is made available, another iteration of the model may be performed to determine an updated recommended dosing regimen based on the additional data and the recommended schedule includes a recommended time for administering a next dose of the drug to the patient, such that a predicted concentration time profile of the drug in the patient in response to the first pharmaceutical dosing regimen is at or above the target drug exposure level (e.g., a target drug concentration trough level) at the recommended time.); and
(c) repeating step (b) (Paragraph [0005] discusses when additional data is made available, another iteration of the model may be performed to determine an updated recommended dosing regimen based on the additional data. This process may be repeated any number of times to reflect any new data that describes the patient.).
Therefore, it would have been obvious to one of ordinary skill in the art to modify Tang to include, (b) applying the curve network to update input data, the updated input data comprising the initial input data and all subsequently-generated concentration-time points; and (c) repeating step (b), as taught by Mould, in order to provide ways to quickly adjust a dosing regimen recommendation for a specific patient, in order to react to fast changes in the patient's medical condition. (Mould Abstract.).
Regarding claim 11, Tang does not explicitly disclose wherein:
determining a dosing regimen comprises selecting a dosing regimen corresponding to one of the inputs based on its respective output.
Mould teaches:
determining a dosing regimen comprises selecting a dosing regimen corresponding to one of the inputs based on its respective output (Paragraphs [0013], [0083]-[0084], [0113], and FIG. 3 discuss the model provides a recommended dosing regimen to a user interface, inputs into the system may be used to update and refine the model for a specific patient taking a specific drug, for example, the dosing regimen output by the model may correspond to the first pharmaceutical regimen or the second pharmaceutical dosing recommendation, the output of the model corresponds to a dosing regimen or schedule that achieves an optimal target level for a physiological parameter of the patient.).
Therefore, it would have been obvious to one of ordinary skill in the art to modify Tang to include, determining a dosing regimen comprises selecting a dosing regimen corresponding to one of the inputs based on its respective output, as taught by Mould, in order to provide ways to quickly adjust a dosing regimen recommendation for a specific patient, in order to react to fast changes in the patient's medical condition. (Mould Abstract.).
Regarding claim 12, Tang does not explicitly disclose wherein:
determining the dosing regimen comprises determining, for each output, the value of one or more pharmacological parameter; and
selecting the dosing regimen comprises selecting the dosing regimen based on the value of the one or more pharmacological parameter.
Mould teaches:
determining the dosing regimen comprises determining, for each output, the value of one or more pharmacological parameter (Paragraphs [0005] and [0125] discuss determine a patient-specific pharmaceutical dosing regimen for a patient and the computational model may generate one or more predicted concentration time profiles of the drug in the patient's body in response to a pharmaceutical dosing regimen, and these one or more profiles may be displayed to a user.); and
selecting the dosing regimen comprises selecting the dosing regimen based on the value of the one or more pharmacological parameter (Paragraphs [0084] and [0125] discuss the computational model may generate one or more predicted concentration time profiles of the drug in the patient's body in response to a pharmaceutical dosing regimen, and these one or more profiles may be displayed to a user, and upon viewing the recommended dosing regimen over the user interface, a medical professional may select to administer the recommending dosing regimen as recommended, or the medical professional may select to slightly alter the recommended dosing regimen.).
Therefore, it would have been obvious to one of ordinary skill in the art to modify Tang to include, determining the dosing regimen comprises determining, for each output, the value of one or more pharmacological parameter; and selecting the dosing regimen comprises selecting the dosing regimen based on the value of the one or more pharmacological parameter, as taught by Mould, in order to provide ways to quickly adjust a dosing regimen recommendation for a specific patient, in order to react to fast changes in the patient's medical condition. (Mould Abstract.).
Claim 13 is rejected under 35 U.S.C. 103 as being unpatentable over Tang in view of Mould and in further view of Ambrose (U.S. Pub. No. 2019/0134070 A1).
Regarding claim 13, Tang does not explicitly disclose wherein:
the output corresponding to each input comprises a concentration-time curve comprising a plurality of concentration-time points; and
the pharmacological parameter is the area under the respective concentration-time curve (AIC);
the proportion of time for which the concentration of the species exceeds a minimum inhibitory concentration (MIC);
the AUC/MIC ratio;
the maximum concentration value in the concentration-time curve; or
the minimum concentration value in the concentration-time curve.
Mould teaches:
the output corresponding to each input comprises a concentration-time curve comprising a plurality of concentration-time points (Paragraphs [0134]-[0135] discuss provide a predicted concentration profile curve for Patient A based on the input dosing regimen, the curve is the time concentration profile as predicted by the computerized recommendation system.); and
the pharmacological parameter is the area under the respective concentration-time curve (AIC) (Paragraph [0016] discusses target drug concentration level may include a target drug concentration trough level; a target drug concentration maximum; a target drug area under the concentration time curve (AUC);
the proportion of time for which the concentration of the species exceeds a minimum inhibitory concentration (MIC) (Paragraphs [0011], [0016] discuss it is generally desirable to maintain an exposure to the drug that is nearly constant, within a specific range, or above a minimum exposure such as a trough value.);
the maximum concentration value in the concentration-time curve (Paragraph [0016] discusses target drug concentration level may include a target drug concentration maximum under the concentration curve.); or
the minimum concentration value in the concentration-time curve (Paragraph [0016] discusses target drug concentration level may include a target drug concentration trough under the concentration curve.).
Therefore, it would have been obvious to one of ordinary skill in the art to modify Tang to include, the output corresponding to each input comprises a concentration-time curve comprising a plurality of concentration-time points; and the pharmacological parameter is the area under the respective concentration-time curve (AIC); the proportion of time for which the concentration of the species exceeds a minimum inhibitory concentration (MIC); the maximum concentration value in the concentration-time curve; or the minimum concentration value in the concentration-time curve, as taught by Mould, in order to provide ways to quickly adjust a dosing regimen recommendation for a specific patient, in order to react to fast changes in the patient's medical condition. (Mould Abstract.).
Ambrose teaches:
the AUC/MIC ratio (Paragraph [0003] discusses the PK-PD measure includes the ratio of the area under the concentration-time at 24 hours to the MIC.).
Therefore, it would have been obvious to one of ordinary skill in the art to modify Tang to include, the AUC/MIC ratio, as taught by Ambrose, in order to provide ways to quickly adjust a dosing regimen recommendation for a specific patient, in order to decreasing the potential for on-therapy drug resistance. (Ambrose Paragraph [0007].).
Claims 14-15 are rejected under 35 U.S.C. 103 as being unpatentable over Tang in view of Mould and in further view of Hirt (U.S. Pub. No. 2022/0328137 A1).
Regarding claim 14, Tang does not explicitly disclose wherein:
selecting the dosing regimen comprises selecting one or more dosing regimens, the value of the pharmacological parameter calculated for the output corresponding to which is no less than a efficacy threshold; and/or
selecting the dosing regimen comprises selecting one or more dosing regimens, the value of the pharmacological parameter calculated for the output corresponding to which is no more than a predetermined toxicity threshold.
Mould teaches:
selecting the dosing regimen comprises selecting one or more dosing regimens, the value of the pharmacological parameter calculated for the output corresponding to which is no less than a efficacy threshold (Paragraph [0072] discusses the target response T may be selected by a physician based on his/her assessment of the patient's pain tolerance and response to drug therapy, the target response defines a critical trough value corresponding to a threshold concentration level, where it is undesirable for the patient's concentration to be below the critical trough value. For example, the target trough T may be 10 ug/mL for infliximab. The systems and methods of the present disclosure may be configured to provide dosing regimen recommendations such that the concentration data in the patient is not predicted to fall substantially below this target trough at any point in time, but instead approaches the target trough value at the time the next dose is administered to the patient.); and/or
selecting the dosing regimen comprises selecting one or more dosing regimens, the value of the pharmacological parameter calculated for the output (Paragraphs [0084] and [0125] discuss the computational model may generate one or more predicted concentration time profiles of the drug in the patient's body in response to a pharmaceutical dosing regimen, and these one or more profiles may be displayed to a user, and upon viewing the recommended dosing regimen over the user interface, a medical professional may select to administer the recommending dosing regimen as recommended, or the medical professional may select to slightly alter the recommended dosing regimen.).
Therefore, it would have been obvious to one of ordinary skill in the art to modify Tang to include, selecting the dosing regimen comprises selecting one or more dosing regimens, the value of the pharmacological parameter calculated for the output corresponding to which is no less than a efficacy threshold; and/or selecting the dosing regimen comprises selecting one or more dosing regimens, the value of the pharmacological parameter calculated for the output, as taught by Mould, in order to provide ways to quickly adjust a dosing regimen recommendation for a specific patient, in order to react to fast changes in the patient's medical condition. (Mould Abstract.).
Hirt teaches:
output corresponding to which is no more than a predetermined toxicity threshold (Paragraphs [0164], [0172], [0193] discuss indicate whether the residual concentration is satisfactory, insufficient or toxic together with background information relating to the concentration-effect relationships which have been referred to for setting the limit and/or toxic concentrations, calculate one or more of the following dosing regimens (i.e. dose, dose interval, infusion duration) which are adapted to reach the efficiency target while meeting the toxicity constraints.).
Therefore, it would have been obvious to one of ordinary skill in the art to modify Tang to include, output corresponding to which is no more than a predetermined toxicity threshold, as taught by Hirt, in order to provide an optimal drug dosing regimen that can be adapted individually to each patient. (Hirt Paragraph [0007].).
Regarding claim 15, Tang does not explicitly disclose wherein:
selecting the dosing regimen comprises selecting one or more dosing regimens, the value of the minimum concentration calculated for the output corresponding to which is no less than an efficacy threshold; and
selecting the dosing regiment comprises selecting one or more dosing regimens, the value of the maximum concentration calculated for the output corresponding to which is no more than a toxicity threshold.
Mould teaches:
selecting the dosing regimen comprises selecting one or more dosing regimens, the value of the minimum concentration calculated for the output corresponding to which is no less than an efficacy threshold (Paragraph [0016] discusses the target response may be selected by a physician based on his/her assessment of the patient's tolerance and response to drug therapy. In an example, the target response includes a target drug concentration level of a drug in a sample obtained from the patient (such as a concentration maximum, minimum, or exposure window), and may be used to determine when a patient should receive a next dose and an amount of that next dose.); and/or
selecting the dosing regiment comprises selecting one or more dosing regimens, the value of the maximum concentration calculated for the output (Paragraphs [0016] discuss target response may be selected by a physician based on his/her assessment of the patient's tolerance and response to drug therapy. In an example, the target response includes a target drug concentration level of a drug in a sample obtained from the patient (such as a concentration maximum, minimum, or exposure window), and may be used to determine when a patient should receive a next dose and an amount of that next dose. The target drug concentration level may include a target drug concentration maximum.).
Therefore, it would have been obvious to one of ordinary skill in the art to modify Tang to include, selecting the dosing regimen comprises selecting one or more dosing regimens, the value of the minimum concentration calculated for the output corresponding to which is no less than an efficacy threshold; and selecting the dosing regiment comprises selecting one or more dosing regimens, the value of the maximum concentration calculated for the output, as taught by Mould, in order to provide ways to quickly adjust a dosing regimen recommendation for a specific patient, in order to react to fast changes in the patient's medical condition. (Mould Abstract.).
Hirt teaches:
output corresponding to which is no more than a toxicity threshold (Paragraphs [0164], [0172], [0193] discuss indicate whether the residual concentration is satisfactory, insufficient or toxic together with background information relating to the concentration-effect relationships which have been referred to for setting the limit and/or toxic concentrations, calculate one or more of the following dosing regimens (i.e. dose, dose interval, infusion duration) which are adapted to reach the efficiency target while meeting the toxicity constraints.).
Therefore, it would have been obvious to one of ordinary skill in the art to modify Tang to include, output corresponding to which is no more than a toxicity threshold, as taught by Hirt, in order to provide an optimal drug dosing regimen that can be adapted individually to each patient. (Hirt Paragraph [0007].).
Claims 16-17 and 19-20 are rejected under 35 U.S.C. 103 as being unpatentable over Tang in view of Varshney (U.S. Pub. No. 2019/0156933 A1).
Regarding claim 16, Tang discloses a computer-implemented method for predicting at least one future point on a pharmacokinetic curve for a given species, the computer- implemented method comprising (Paragraphs [0008]-[0009] discuss a method for pharmacokinetic modeling, generate one or more time series predictions include concentration values of a drug in plasma as a function of time following administration of a dose of the drug.):
providing a machine learning algorithm (Paragraphs [0003]-[0004] discuss artificial neural networks (ANN) is a framework for one or more machine learning algorithms to work together and process complex data inputs, the ANN is used in Pharmacokinetic modeling, which predicts how a drug will interact with the human body.);
receiving training data, the training data comprising a plurality of pharmacokinetic curves (Paragraphs [0049] and [0055] discuss method for training an RSNN for pharmacokinetic modeling, the model is iteratively trained using patients from a training set including PK curves.); and
training the machine learning algorithm using the received training data, thereby generating the machine learning model (Paragraph [0049] discusses training an RSNN for pharmacokinetic modeling.).
Tang does not disclose:
generating a machine learning model.
Varshney teaches:
generating a machine learning model (Paragraph [0021] discusses methods in accordance with the present disclosure can be used to generate, train, and execute a full body circulation model.).
Therefore, it would have been obvious to one of ordinary skill in the art to modify Tang to include, generating a machine learning model, as taught by Varshney, in order to accurate representations for specific subjects for estimating drug concentration. (Varshney Paragraph [0003].).
Regarding claim 17, Tang discloses wherein:
the training data includes associated pairs of training data items, the pairs each including an input sequence of concentration-time points, and at least one output concentration-time point (Paragraph [0049] discusses baseline characteristics of the ith patient and d.sub.i is the time sequence of actual dose levels assigned to the ith patient. The variable y.sub.i represents the output from the model, that is, the time sequence of observed pharmacokinetic concentration of the ith patient. The model is iteratively trained using patients from a training set. During the training process, the model compares its generated prediction c.sub.i against the ground-truth data c.sub.i, and updates its weight's.).
Regarding claim 19, Tang discloses further comprising retraining the machine learning algorithm for patients with different pharmacokinetic responses, the pharmacokinetic responses defined by a profile comprising one or more parameters of a physiologically-based pharmacokinetic model which is usable to simulate a patient's pharmacokinetic response, the computer-implemented method further comprising (Paragraph [0049] discusses training an RSNN for pharmacokinetic modeling using the output and input pair, {y.sub.i,{tilde over (x)}.sub.i}.sub.i=1.sup.k, where {tilde over (x)}.sub.i=(x.sub.i, d.sub.i) are the inputs to the model; the model is iteratively trained using patients from a training set, the variable y.sub.i represents the output from the model, that is, the time sequence of observed pharmacokinetic concentration of the ith , the variable x.sub.i is a p-dimensional vector representing the p baseline characteristics of the ith patient and d.sub.i is the time sequence of actual dose levels assigned to the ith patient.):
generating simulated pharmacokinetic curve training data using the physiologically-based pharmacokinetic model and the parameters in the profile (Paragraphs [0021] discuss in pharmacokinetic modeling, time invariant data such as baseline characteristics of a patient (e.g., age, sex, etc), and time variant data such as dose levels of a drug in a patient, are used to generate a Pk curve that shows the concentration of the drug in the blood plasma over an interval of time.; and
retraining the machine learning algorithm using the simulated pharmacokinetic curve training data (Paragraph [0049] discusses model is iteratively trained using patients from a training set. During the training process, the model compares its generated prediction c.sub.i against the ground-truth data c.sub.i, and updates its weight's accordingly.).
Regarding claim 20, Tang discloses wherein:
when retraining the machine learning algorithm, one or more of the following are held constant (Paragraph [0049] discusses the model is iteratively trained using patients from a training set.):
one or more LSTM layers of the dose network (Paragraph [0042] discusses a LSTM RNN unit refers to an RNN unit that includes a cell, an input gate, and output gate, and a forget gate. The cell remembers values over arbitrary time intervals and the three gates regulate the flow of information. A LSTM RNN unit can minimize the impact of the vanishing gradient problems known to be encountered in some instances when training a traditional RNN.).
Claim 18 is rejected under 35 U.S.C. 103 as being unpatentable over Tang in view of Varshney and in further view of Mould.
Regarding claim 18, Tang discloses wherein:
the machine learning algorithm comprises (Paragraphs [0003]-[0004] discuss artificial neural networks (ANN) is a framework for one or more machine learning algorithms to work together and process complex data inputs, the ANN is used in Pharmacokinetic modeling, which predicts how a drug will interact with the human body.):
a curve network, which is an artificial neural network configured to output one or more subsequent concentration-time points which would be expected in the absence of an administration of a dose of the given species Paragraph [0024] discusses the residual semi-recurrent neural network includes a multilayer perceptron (MLP) for receiving and processing time invariant data, if being used for Pk modeling, the data pertaining to patient baseline characteristics are provided to the MLP, and data pertaining to the dose level of a drug given to a patient at sequential points in time is provided to the RNN, the output of the RNN and the MLP can also be combined to generate a Pk curve showing the relationship between the concentration of a drug in the plasma of a patient and the time after a single dose of the drug has been administered to a patient.); and
a dose network, which is an artificial neural network configured to output one or more values indicative of concentration of the given species after a dose has been administered (Paragraphs [0011], [0024] and [0035] discuss provides residual semi-recurrent neural networks configured to process both time invariant data and time variant data in an efficient manner that improves prediction accuracy, the MLP output can result from processing input data associated with patient baseline characteristics, and the time invariant data can be a sequence of cumulative amounts of a drug injected into a patient, the output of the RNN unit (the time series prediction) can be a Pk curve and the one or more time series predictions can include concentration values of a drug in plasma as a function of time following administration of a dose of the drug.); and
training the machine learning algorithm comprises (Paragraph [0049] discusses training an RSNN for pharmacokinetic modeling.):
training the curve network using curve network training data, thereby establishing a plurality of curve network weights (Paragraphs [0004], [0030], and [0048]-[0051] discuss the artificial neurons and edges typically have a weight that can adjusts while the ANN is being trained, the learned weights/activation functions can be adjusted/tuned by using training datasets to teach the neural network to associate certain features of the data sets with certain results.);
fixing the curve network weights (Paragraphs [0004], [0030], and [0048]-[0051] discuss the learned weights/activation functions can be adjusted/tuned by using training datasets to teach the neural network to associate certain features of the data sets with certain results.);
inputting dose network training data comprising at least an input sequence of concentration-time points including a peak concentration-time point immediately after the administration of a dose, and dosage data (Paragraphs [0021], [0024] discuss in pharmacokinetic modeling, time invariant data such as baseline characteristics of a patient (e.g., age, sex, etc), and time variant data such as dose levels of a drug in a patient, are used to generate a Pk curve that shows the concentration of the drug in the blood plasma over an interval of time, data pertaining to the dose level of a drug given to a patient at sequential points in time is provided to the RNN.); and
inputting output data comprising at least one concentration-time point as would be determined by the whole machine learning algorithm (Paragraphs [0008]-[0009] discuss neural network can be configured to combine the MPL output with the RNN output to generate a residual output. The one or more time series predictions can be generated based at least partially on the residual output. The one or more time series predictions can include concentration values of a drug in plasma as a function of time following administration of a dose of the drug, output from the MPL is received by a RNN unit.).
Tang does not explicitly disclose:
one or more values indicative of an increase in concentration of the given species after a dose has been administered.
Mould teaches:
one or more values indicative of an increase in concentration of the given species after a dose has been administered (Paragraphs [0083]-[0084], [0087] and FIG. 13 discuss dosing regimen includes recommended times and doses to administer one or more pharmaceutical or drugs to the patient, includes increased concentrations and times.).
Therefore, it would have been obvious to one of ordinary skill in the art to modify Tang to include, one or more values indicative of an increase in concentration of the given species after a dose has been administered, as taught by Mould, in order to provide ways to quickly adjust a dosing regimen recommendation for a specific patient, in order to react to fast changes in the patient's medical condition. (Mould Abstract.).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to DAWN TRINAH HAYNES whose telephone number is (571)270-5994. The examiner can normally be reached M-F 7:30-5:15PM.
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, Jason Dunham can be reached on (571)272-8109. 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.
/DAWN T. HAYNES/
Art Unit 3686
/RACHELLE L REICHERT/Primary Examiner, Art Unit 3686
Prosecution Insights