DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Specification
The abstract of the disclosure is objected to because:
The abstract should be in narrative form and generally limited to a single paragraph on a separate sheet within the range of 50 to 150 words in length. The abstract should describe the disclosure sufficiently to assist readers in deciding whether there is a need for consulting the full patent text for details. Currently, the abstract is less than 50 words in length.
A corrected abstract of the disclosure is required and must be presented on a separate sheet, apart from any other text. See MPEP § 608.01(b).
Claim Objections
Claims 1, 3-6, 8, 12, 15-20, and 22-25 are objected to because of the following informalities:
The phrase “as ventilation parameter” should be changed to –as a ventilation parameter—since this is the first time this is mentioned (Claim 1, Line 5).
The phrase “the mechanical ventilation” should be changed to –a mechanical ventilation—since this is the first time this is mentioned (Claim 1, Line 10).
The phrase “the value” should be changed to –a value—since this is the first time this is mentioned (Claim 1, Line 11).
The phrase “the function” should be changed to –the target function—for consistency (Claim 1, Line 17).
The phrase “as ventilation parameter” should be changed to –as the ventilation parameter—for consistency (Claim 1, Lines 22-23).
The phrase “step i)” should be changed to –step (i)—for consistency (Claim 1, Line 23).
The phrase “at least one” should be changed to –the at least one—for consistency (Claim 3, Line 2).
The phrase “random Forrests” should be changed to –random forests—to correct the typographical error (Claim 3, Line 5).
The phrase “at least one” should be changed to –the at least one—for consistency (Claim 4, Line 3).
The phrase “at least one” should be changed to –the at least one—for consistency (Claim 5, Line 2).
The phrase “the expected value of the improvement” should be changed to –an expected value of the improvement—since this is the first time this is mentioned (Claim 5, Lines 3-4).
The phrase” constrains” should be changed to –constraints—to correct the grammatical error (Claim 5, Line 4).
The phrase “at least one” should be changed to –the at least one—for consistency (Claim 6, Line 2).
The phrase “at least one” should be changed to –the at least one—for consistency (Claim 8, Line 3).
The phrase “the lung” should be changed to –a lung—since this is the first time this is mentioned (Claim 12, Line 4).
The phrase “the lung” should be changed to –a lung—since this is the first time this is mentioned (Claim 15, Line 5).
The phrase “at least one” should be changed to –the at least one—for consistency (Claim 15, Line 5).
The phrase “the lung” should be changed to –a lung—since this is the first time this is mentioned (Claim 16, Line 6).
The phrase “at least one” should be changed to –the at least one—for consistency (Claim 16, Line 6).
The phrase “next ventilation parameter values” should be changed to –the at least one next ventilation parameter— (Claim 17, Line 3).
The phrase “the function value” should be changed to –a function value—since this is the first time this is mentioned (Claim 17, Line 4).
The phrase “the indicator function” should be changed to –an indicator function—since this is the first time this is mentioned (Claim 17, Line 6).
The phrase “the function” should be changed to –a function—since this is the first time this is mentioned (Claim 17, Lines 6-7).
The phrase “a predetermined reference value” should be changed to –the predetermined reference value—for consistency (Claim 17, Line 7).
The phrase “the enrichment of gas in the blood of the lung as a function of at least one output parameter” should be changed to –an enrichment of gas in a blood of a lung as a function of the at least one output parameter—for consistency (Claim 17, Lines 8-9).
The phrase “and/or B describes a mechanical loading of the lung as a function of at least one output parameter of the lung model, wherein the at least one output parameter describes a mechanical loading value of the lung of the patient” should be removed since it was already previously recited earlier in Claim 15 which Claim 17 is dependent on (Claim 17, Lines 11-13).
The phrase “the lung” should be changed to –a lung—since this is the first time this is mentioned (Claim 18, Line 3).
The phrase “either” should be removed since there are more than two curves listed (Claim 19, Line 2).
The phrase “the parameterized pressure-time curve” should be changed to –the pressure-time curve—for consistency (Claim 20, Line 2).
The phrase “the patient-specific pressure in the trachea—should be changed to –a patient-specific pressure in a trachea—since this is the first time this is mentioned (Claim 20, Lines 2-3).
The phrase “the mechanical ventilation” should be changed to –a mechanical ventilation—since this is the first time this is mentioned (Claim 22, Line 7).
The phrase “the ventilation parameter” should be changed to –a ventilation parameter—since this is the first time this is mentioned (Claim 22, Line 8).
The phrase “the value” should be changed to –a value—since this is the first time this is mentioned (Claim 22, Line 8).
The phrase “the function” should be changed to –the target function—for consistency (Claim 22, Line 14).
The phrase “as ventilation parameter” should be changed to –as the ventilation parameter—for consistency (Claim 22, Lines 19-20).
The phrase “step i)” should be changed to –step (i)—for consistency (Claim 22, Line 20).
The phrase “the mechanical ventilation” should be changed to –a mechanical ventilation—since this is the first time this is mentioned (Claim 23, Line 7).
The phrase “the ventilation parameter” should be changed to –a ventilation parameter—since this is the first time this is mentioned (Claim 23, Line 8).
The phrase “the value” should be changed to –a value—since this is the first time this is mentioned (Claim 23, Line 8).
The phrase “the function” should be changed to –the target function—for consistency (Claim 23, Line 14).
The phrase “as ventilation parameter” should be changed to –as the ventilation parameter—for consistency (Claim 23, Lines 19-20).
The phrase “step i)” should be changed to –step (i)—for consistency (Claim 23, Line 20).
The phrase “the mechanical ventilation” should be changed to –a mechanical ventilation—since this is the first time this is mentioned (Claim 24, Line 12).
The phrase “the ventilation parameter” should be changed to –a ventilation parameter—since this is the first time this is mentioned (Claim 24, Line 13).
The phrase “the value” should be changed to –a value—since this is the first time this is mentioned (Claim 24, Line 13).
The phrase “the function” should be changed to –the target function—for consistency (Claim 24, Line 19).
The phrase “as ventilation parameter” should be changed to –as the ventilation parameter—for consistency (Claim 24, Lines 24-25).
The phrase “step i)” should be changed to –step (i)—for consistency (Claim 24, Line 25).
The phrase “Ventilation machine” should be changed to –A ventilation machine—since this is the first time this is mentioned (Claim 25, Line 1).
The phrase “the at least one data processing device” should be changed to –the data processing device—for consistency (Claim 25, Line 3).
The phrase “the mechanical ventilation” should be changed to –a mechanical ventilation—since this is the first time this is mentioned (Claim 25, Line 12).
The phrase “the ventilation parameter” should be changed to –a ventilation parameter—since this is the first time this is mentioned (Claim 25, Line 13).
The phrase “the value” should be changed to –a value—since this is the first time this is mentioned (Claim 25, Line 13).
The phrase “the function” should be changed to –the target function—for consistency (Claim 25, Line 19).
The phrase “as ventilation parameter” should be changed to –as the ventilation parameter—for consistency (Claim 25, Lines 24-25).
The phrase “step i)” should be changed to –step (i)—for consistency (Claim 25, Line 25).
The phrase “θb,next” should be changed to --θb,next—for consistency (Claim 25, Line 24).
The phrase “θb,i” should be changed to --θb,i—for consistency (Claim 25, Line 25).
Appropriate correction is required.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 3, 5, 8, 12-17, 19, and 20 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 3 states “other regression models” (Line 5). This statement is indefinite because it is unclear what these “other regression models” are. It appears the applicant was trying to say regression models. However, it is not clear on what the “other” regression models are since they’re never listed. Therefore, the regression models involved cannot be determined. For examination purposes, the claim limitation will be interpreted as “regression models”.
Claim 3 states “an algorithm” (Line 3). This statement is indefinite because it is unclear how many algorithms are required in the claim. It appears the applicant was trying to say one of the listed algorithms is required. However, the use of “in particular” creates confusion regarding whether or not the first algorithm listed is a required algorithm. Additionally, it is unclear if the subsequent algorithms listed are further describing the first algorithm listed. Therefore, the number of algorithms involved cannot be determined. For examination purposes, the claim limitation will be interpreted as there is at least one algorithm involved and that the other algorithms listed are separate algorithms that aren’t further describing the first algorithm.
Claim 5 states “the expected value of the improvement” (Line 4). This statement is indefinite because it is unclear what value this is in reference to. It appears the applicant was trying to say this is in relation to a type of Bayesian acquisition function. However, the expected value of the improvement can be the predetermined reference value, a known clinical value, the optimized ventilation parameter, or something else. The claim does not make it clear that this is related to a particular kind of Bayesian acquisition function. Therefore, the identity of the expected value of the improvement cannot be determined. For examination purposes, the claim limitation will be interpreted as this is the predetermined reference value, a known clinical value, and/or a type of Bayesian acquisition function.
Claim 8 states “provided in step (ii)”, “the selection process”, “the model evaluations”, and “the results” (Lines 2-6). There is insufficient antecedent basis for this limitation in the claim. It appears the applicant was trying to say the selection process is step (ii), the model evaluations is step (i), and the results are step (iii). However, the claim limitation does not make it clear that these are the steps being referred to and the claim limitation could be in reference to completely different steps. Additionally, the use of “provided in step (ii)” creates confusion regarding whether or not the claim limitation is limited to only step (ii) or to the other steps mentioned in Claim 1. Therefore, the steps involved cannot be determined. For examination purposes, the claim limitation will be interpreted as the selection process is step (ii), the model evaluations is step (i), and the results are step (iii).
Claim 8 states “other computing units” (Line 6). This statement is indefinite because it is unclear how many computing units are involved and what these “other computing units” entail. It appears the applicant was trying to say there are multiple computing units and the computing units are duplicates of each other. However, the use of “other” creates confusion regarding whether or not this computing unit is same in structure to the one mentioned earlier in the claim. Therefore, the number of computing units involved cannot be determined. For examination purposes, the claim limitation will be interpreted as there are at least two duplicate computing units involved.
Claim 12 states “a patient-specific reference value” (Lines 2-3). This statement is indefinite because it is unclear if this value is the same as the predetermined reference value of Claim 1. It appears the applicant was trying to say they’re the same. However, the values could be completely distinct. Therefore, then number of values involved cannot be determined. For examination purposes, the claim limitation will be interpreted as they’re the same.
Claim 13 states “the ventilation parameter values” (Line 2). This statement is indefinite because it is unclear which ventilation parameter values these are in reference to. It appears the applicant was trying to say the optimal ventilation parameter. However, it is possible this is in reference to the ventilation parameter that’s been used for the next ventilation parameter. Therefore, the ventilation parameter involved cannot be determined. For examination purposes, the claim limitation will be interpreted as the next ventilation parameter that has taken the place of the ventilation parameter.
Claim 14 states “a set of initial input respiration parameter values” (Line 2). This statement is indefinite because it is unclear how many of these values are involved and whether or not they’re the same as the ones mentioned in Claim 1. It appears the applicant was trying to say that since this is a set, there are at least two initial input respiration parameter values involved and that one of them is the same as the one mentioned in Claim 1. However, the confusion arises due to the values being mentioned as a set with no connection to Claim 1. Therefore, the number of values involved cannot be determined. For examination purposes, the claim limitation will be interpreted as since this is a set, there are at least two initial input respiration parameter values involved and that one of them is the same as the one mentioned in Claim 1.
Claim 15 states “the function values of function B” (Line 2). There is insufficient antecedent basis for this limitation in the claim. It appears the applicant was trying to say “function values of function B”. However, since this is the first time this is mentioned, it is unclear what it is referring back to. Therefore, the identity of the term cannot be determined. For examination purposes, the claim limitation will be interpreted as “function values of function B”. Similar rejections are applied to Claim 16.
Claim 16 states “the set of next input ventilation parameters” (Line 4). There is insufficient antecedent basis for this limitation in the claim. It appears the applicant was trying to say “a set of next input ventilation parameters”. However, since this is the first time this is mentioned, it is unclear what it is referring back to. Therefore, the identity of the term cannot be determined. For examination purposes, the claim limitation will be interpreted as “a set of next input ventilation parameters”.
Claim 16 states “further training of the Gaussian process” (Line 5). This statement is indefinite because it is unclear when the first training happened and there is insufficient antecedent basis for the Gaussian process. It appears the applicant was trying to say that Claim 16 is dependent on Claim 15. However, the first training and the Gaussian process were never previously recited. Therefore, the trainings and processes involved cannot be determined. For examination purposes, the claim limitation will be interpreted as Claim 16 is dependent on Claim 15.
Claim 19 states “before the method is started” (Line 2). This statement is indefinite because it is unclear which method step this is in reference to. It appears the applicant was trying to say before step (i). However, since Claim 1 has multiple method steps involved, it is unclear when this step is performed. Therefore, the timing of the step cannot be determined. For examination purposes, the claim limitation will be interpreted as before step (i).
Claim 19 states “curves of the patient derived therefrom” (Line 6). This statement is indefinite because it is unclear what curves this is in reference to. It appears the applicant was trying to say curves of the patient derived from the earlier listed curves. However, it is possible that the curves can be any type of curve that is patient derived. Therefore, the number of curves involved cannot be determined. For examination purposes, the claim limitation will be interpreted as any type of curve that is patient derived.
Claim 19 states “which comprises at least one breath” (Lines 6-7). This statement is indefinite because it is unclear whether or not the at least one breath applies to all curves or just the curves of the patient derived. It appears the applicant was trying to say only the curves of the patient derived. However, the phrase “which comprises” creates confusion regarding which curves comprises the at least one breath of the patient. Therefore, the number of curves involved cannot be determined. For examination purposes, the claim limitation will be interpreted as only the curves of the patient derived.
Claim 17 is rejected for being dependent on rejected Claim 15.
Claim 20 is rejected for being dependent on rejected Claim 19.
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.
Claims 1, 5, 8, 12, and 22-25 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Karbing et al. (US 2017/0255756 A1).
Regarding Claim 1, Karbing discloses a method for automatically determining at least one optimal ventilation parameter θb,opt for operating a ventilation machine (invention allows for optimization of all ventilator settings across different levels of PEEP, paragraph 0016), comprising the computer- implemented steps of: Providing a patient-specific digital lung model (control means may comprise one or more PEEP models, PEEP models allow use of physiological models to simulate effect of PEEP on the effect of changes in other mechanical ventilator settings by input to models of lung mechanics, paragraph 0060), inputting at least one initial input ventilation parameter θb,init as ventilation parameter θb,i = θb,init (PEEP models 20 shown to be inputted into the physiological models, Fig 3; the learning module having a set of a priori settings of PEEP model parameters (MOD_P_PEEP), paragraph 0060; PEEP models start off as input, Fig 3); performing the following steps (i) to (iii) iteratively until a completion criterion is met which checks the reaching of an optimal patient-specific ventilation parameter θb,i = θb,opt (the optimal setting of remaining ventilator settings can be found through model simulation of clinical outcome variables and optimisation of settings according to for example a set of clinical preference functions (CPFs), or a rule set, paragraph 0105) and/or checks the reaching of a predetermined number of iterations (possible to simulate for all plausible values of PEEP, either iteratively going through all possible values or by a numerical method searching through the PEEP values, thus locating the optimal PEEP value which can be advised to the clinician, paragraph 0105); i) Evaluation of the mechanical ventilation simulated on the lung model as a function of the ventilation parameter θb,i by determining the value of at least one patient-specific target function F=F(θb,i) from the lung model (model parameter of a physiological model as a function of the PEEP settings, control means may comprise one or more PEEP models, PEEP models allow use of physiological models to simulate effect of PEEP on the effect of changes in other mechanical ventilator settings by input to models of lung mechanics, paragraph 0060; PEEP models are inputted into model parameters which lead to outputs or outcome variables, Fig 3), wherein the target function F describes a lung reaction to the simulated mechanical ventilation as a function of at least one output parameter of the lung model (control means may comprise one or more PEEP models, PEEP models allow use of physiological models to simulate effect of PEEP on the effect of changes in other mechanical ventilator settings by input to models of lung mechanics, paragraph 0060; the PEEP models inputted would cause a lung reaction or response when inputted into the physiological models, Fig 3), ii) Evaluating the at least one determined value of the function F on the basis of at least one predetermined reference value (the optimal setting of remaining ventilator settings can be found through model simulation of clinical outcome variables and optimisation of settings according to for example a set of clinical preference functions (CPFs), or a rule set, paragraph 0105; a plurality of clinical preference functions (CPFs) relating settings of positive end expiratory pressure (PEEP) for the ventilation means to a corresponding set of clinical outcome variables to connect the decision support with clinical practise and experience, paragraph 0064; outcome variables are compared with clinical outcome variables that come from clinical practice and experience, Fig 3), and selecting at least one next ventilation parameter θb,next, using a selection method dependent on at least one previously used ventilation parameter θb,i (possible to simulate for all plausible values of PEEP, either iteratively going through all possible values or by a numerical method searching through the PEEP values, thus locating the optimal PEEP value which can be advised to the clinician, paragraph 0105; PEEP models may be adapted to the patient by a learning module, the learning module having a set of a priori settings of PEEP model parameters (MOD_P_PEEP) based on the currently measured model parameter (MOD_P) value of the corresponding physiological models (MOD), preferably based on a Bayesian distribution based on patient type and/or clinical condition, paragraph 0060; plausible values of PEEP are chosen iteratively, Fig 3; PEEP goes through a learning process, Fig 8) iii) Using the at least one next ventilation parameter θb,next as ventilation parameter θb,i to determine F=F(θb,i = θb,next) in step (i) (possible to simulate for all plausible values of PEEP, either iteratively going through all possible values or by a numerical method searching through the PEEP values, thus locating the optimal PEEP value which can be advised to the clinician, paragraph 0105; PEEP models may be adapted to the patient by a learning module, the learning module having a set of a priori settings of PEEP model parameters (MOD_P_PEEP) based on the currently measured model parameter (MOD_P) value of the corresponding physiological models (MOD), preferably based on a Bayesian distribution based on patient type and/or clinical condition, paragraph 0060; plausible values of PEEP are from repeated simulations of the physiological models, Fig 3; PEEP goes through a learning process, Fig 8); providing the patient-specific optimal ventilation parameter θb,opt if the completion criterion is met (the optimal setting of remaining ventilator settings can be found through model simulation of clinical outcome variables and optimisation of settings according to for example a set of clinical preference functions (CPFs), or a rule set, possible to simulate for all plausible values of PEEP, either iteratively going through all possible values or by a numerical method searching through the PEEP values, thus locating the optimal PEEP value which can be advised to the clinician, paragraph 0105).
It is noted that “providing the patient-specific optimal ventilation parameter” is interpreted as actively providing and operating the ventilator with the patient-specific optimal ventilation parameter.
Regarding Claim 5, Karbing discloses the selection method for selecting at least one next ventilation parameter θb,next includes an acquisition function which uses the expected value of the improvement, in particular taking into account constraints (the optimal setting of remaining ventilator settings can be found through model simulation of clinical outcome variables and optimisation of settings according to for example a set of clinical preference functions (CPFs), or a rule set, paragraph 0105; a plurality of clinical preference functions (CPFs) relating settings of positive end expiratory pressure (PEEP) for the ventilation means to a corresponding set of clinical outcome variables to connect the decision support with clinical practise and experience, paragraph 0064; outcome variables are compared with clinical outcome variables that come from clinical practice and experience, Fig 3; expected values or clinical outcome variables are constrained by what is found in clinical practice and experience).
Regarding Claim 8, Karbing discloses the selection process takes place on a computing unit, in particular a processor, and the model evaluations are carried out in parallel on other computing units and the results are subsequently recombined (invention or some of the features thereof can also be implemented as software running on one or more data processors and/or digital signal processors, paragraph 0125; invention may be implemented in a single unit, or be both physically and functionally distributed between different units and processors, paragraph 0126; the invention being distributed between different units and processors would inherently have the results recombined or combined to produce the full output and functionality of the device).
Regarding Claim 12, Karbing discloses step (ii) of the method includes that, as a patient-specific reference value, an oxygen saturation SO2 must not be undershot (CPFs may be understood as a means for relating settings on the mechanical ventilator to a corresponding set of clinical outcome variables by associating said different values of said outcome variables with a level of preference, a level of oxygen saturation in the arterial blood of 95% is preferable to 94%, and 95% is therefore in the CPF associated with greater preference and this may be related to changing the inspired oxygen on the mechanical ventilator, paragraph 0064; the plurality of clinical preference functions (CPFs) may be applied for providing decision support related to an overall optimisation of the PEEP setting of the mechanical ventilation for the patient, paragraph 0066).
Regarding Claim 22, Karbing discloses a computer program product using a digital lung model (PEEP models allow use of physiological models to simulate effect of PEEP on the effect of changes in other mechanical ventilator settings by input to models of lung mechanics, paragraph 0060; invention or some of the features thereof can also be implemented as software running on one or more data processors and/or digital signal processors, paragraph 0125; invention may be implemented in a single unit, or be both physically and functionally distributed between different units and processors, paragraph 0126), comprising instructions which, when executed on a processor of a data processing unit, cause the following steps (i) through (iii) to be performed iteratively until a completion criterion is met which tests for the achievement of optimal patient- specific ventilation parameters θb,i = θb,opt (the optimal setting of remaining ventilator settings can be found through model simulation of clinical outcome variables and optimisation of settings according to for example a set of clinical preference functions (CPFs), or a rule set, paragraph 0105) and/or provides for the achievement of a predetermined number of iterations (possible to simulate for all plausible values of PEEP, either iteratively going through all possible values or by a numerical method searching through the PEEP values, thus locating the optimal PEEP value which can be advised to the clinician, paragraph 0105); i) Evaluation of the mechanical ventilation simulated on the lung model as a function of the ventilation parameter θb,i by determining the value of at least one patient-specific target function F=F(θb,i) from the lung model (model parameter of a physiological model as a function of the PEEP settings, control means may comprise one or more PEEP models, PEEP models allow use of physiological models to simulate effect of PEEP on the effect of changes in other mechanical ventilator settings by input to models of lung mechanics, paragraph 0060; PEEP models are inputted into model parameters which lead to outputs or outcome variables, Fig 3), wherein the target function F describes a lung reaction to the simulated mechanical ventilation as a function of at least one output parameter of the lung model (control means may comprise one or more PEEP models, PEEP models allow use of physiological models to simulate effect of PEEP on the effect of changes in other mechanical ventilator settings by input to models of lung mechanics, paragraph 0060; the PEEP models inputted would cause a lung reaction or response when inputted into the physiological models, Fig 3), ii) Evaluating the at least one determined value of the function F on the basis of at least one predetermined reference value (the optimal setting of remaining ventilator settings can be found through model simulation of clinical outcome variables and optimisation of settings according to for example a set of clinical preference functions (CPFs), or a rule set, paragraph 0105; a plurality of clinical preference functions (CPFs) relating settings of positive end expiratory pressure (PEEP) for the ventilation means to a corresponding set of clinical outcome variables to connect the decision support with clinical practise and experience, paragraph 0064; outcome variables are compared with clinical outcome variables that come from clinical practice and experience, Fig 3), and selecting at least one next ventilation parameter θb,next, using a selection method dependent on at least one previously used ventilation parameter θb,i (possible to simulate for all plausible values of PEEP, either iteratively going through all possible values or by a numerical method searching through the PEEP values, thus locating the optimal PEEP value which can be advised to the clinician, paragraph 0105; PEEP models may be adapted to the patient by a learning module, the learning module having a set of a priori settings of PEEP model parameters (MOD_P_PEEP) based on the currently measured model parameter (MOD_P) value of the corresponding physiological models (MOD), preferably based on a Bayesian distribution based on patient type and/or clinical condition, paragraph 0060; plausible values of PEEP are chosen iteratively, Fig 3; PEEP goes through a learning process, Fig 8) iii) Using the at least one next ventilation parameter θb,next as ventilation parameter θb,i to determine F=F(θb,i = θb,next) in step (i) (possible to simulate for all plausible values of PEEP, either iteratively going through all possible values or by a numerical method searching through the PEEP values, thus locating the optimal PEEP value which can be advised to the clinician, paragraph 0105; PEEP models may be adapted to the patient by a learning module, the learning module having a set of a priori settings of PEEP model parameters (MOD_P_PEEP) based on the currently measured model parameter (MOD_P) value of the corresponding physiological models (MOD), preferably based on a Bayesian distribution based on patient type and/or clinical condition, paragraph 0060; plausible values of PEEP are from repeated simulations of the physiological models, Fig 3; PEEP goes through a learning process, Fig 8).
It is noted that “achievement of patient-specific optimal ventilation parameters” is interpreted as actively achieving and operating the ventilator or device with the patient-specific optimal ventilation parameters.
Regarding Claim 23, Karbing discloses a computer readable medium having stored thereon a computer program product utilizing a digital lung model (PEEP models allow use of physiological models to simulate effect of PEEP on the effect of changes in other mechanical ventilator settings by input to models of lung mechanics, paragraph 0060; invention or some of the features thereof can also be implemented as software running on one or more data processors and/or digital signal processors, paragraph 0125; invention may be implemented in a single unit, or be both physically and functionally distributed between different units and processors, paragraph 0126) and comprising instructions which, when executed on a processor of a data processing unit, cause the following steps (i) through (iii) to be performed iteratively until a completion criterion is met which tests for the achievement of optimal patient- specific ventilation parameters θb,i = θb,opt (the optimal setting of remaining ventilator settings can be found through model simulation of clinical outcome variables and optimisation of settings according to for example a set of clinical preference functions (CPFs), or a rule set, paragraph 0105) and/or provides for the achievement of a predetermined number of iterations (possible to simulate for all plausible values of PEEP, either iteratively going through all possible values or by a numerical method searching through the PEEP values, thus locating the optimal PEEP value which can be advised to the clinician, paragraph 0105); i) Evaluation of the mechanical ventilation simulated on the lung model as a function of the ventilation parameter θb,i by determining the value of at least one patient-specific target function F=F(θb,i) from the lung model (model parameter of a physiological model as a function of the PEEP settings, control means may comprise one or more PEEP models, PEEP models allow use of physiological models to simulate effect of PEEP on the effect of changes in other mechanical ventilator settings by input to models of lung mechanics, paragraph 0060; PEEP models are inputted into model parameters which lead to outputs or outcome variables, Fig 3), wherein the target function F describes a lung reaction to the simulated mechanical ventilation as a function of at least one output parameter of the lung model (control means may comprise one or more PEEP models, PEEP models allow use of physiological models to simulate effect of PEEP on the effect of changes in other mechanical ventilator settings by input to models of lung mechanics, paragraph 0060; the PEEP models inputted would cause a lung reaction or response when inputted into the physiological models, Fig 3), ii) Evaluating the at least one determined value of the function F on the basis of at least one predetermined reference value (the optimal setting of remaining ventilator settings can be found through model simulation of clinical outcome variables and optimisation of settings according to for example a set of clinical preference functions (CPFs), or a rule set, paragraph 0105; a plurality of clinical preference functions (CPFs) relating settings of positive end expiratory pressure (PEEP) for the ventilation means to a corresponding set of clinical outcome variables to connect the decision support with clinical practise and experience, paragraph 0064; outcome variables are compared with clinical outcome variables that come from clinical practice and experience, Fig 3), and selecting at least one next ventilation parameter θb,next, using a selection method dependent on at least one previously used ventilation parameter θb,i (possible to simulate for all plausible values of PEEP, either iteratively going through all possible values or by a numerical method searching through the PEEP values, thus locating the optimal PEEP value which can be advised to the clinician, paragraph 0105; PEEP models may be adapted to the patient by a learning module, the learning module having a set of a priori settings of PEEP model parameters (MOD_P_PEEP) based on the currently measured model parameter (MOD_P) value of the corresponding physiological models (MOD), preferably based on a Bayesian distribution based on patient type and/or clinical condition, paragraph 0060; plausible values of PEEP are chosen iteratively, Fig 3; PEEP goes through a learning process, Fig 8) iii) Using the at least one next ventilation parameter θb,next as ventilation parameter θb,i to determine F=F(θb,i = θb,next) in step (i) (possible to simulate for all plausible values of PEEP, either iteratively going through all possible values or by a numerical method searching through the PEEP values, thus locating the optimal PEEP value which can be advised to the clinician, paragraph 0105; PEEP models may be adapted to the patient by a learning module, the learning module having a set of a priori settings of PEEP model parameters (MOD_P_PEEP) based on the currently measured model parameter (MOD_P) value of the corresponding physiological models (MOD), preferably based on a Bayesian distribution based on patient type and/or clinical condition, paragraph 0060; plausible values of PEEP are from repeated simulations of the physiological models, Fig 3; PEEP goes through a learning process, Fig 8).
It is noted that “achievement of patient-specific optimal ventilation parameters” is interpreted as actively achieving and operating the ventilator or device with the patient-specific optimal ventilation parameters.
Regarding Claim 24, Karbing discloses a system (system of Fig 2) comprising at least one data processing device and a computer program product (12, Fig 2; control means integrated on a computer system, paragraph 0098; invention can be implemented by means of hardware, software, firmware or any combination of these, software running on one or more data processors and/or digital signal processors, paragraph 0125), wherein the at least one data processing device is configured to execute the computer program product and, in particular, to exchange data with a ventilation machine (11, Fig 2) for controlling the ventilation machine (control means may be integrated on a computer system operationally connected to the ventilation means 11, paragraph 0098), wherein the computer program product uses a digital lung model (PEEP models allow use of physiological models to simulate effect of PEEP on the effect of changes in other mechanical ventilator settings by input to models of lung mechanics, paragraph 0060; invention or some of the features thereof can also be implemented as software running on one or more data processors and/or digital signal processors, paragraph 0125; invention may be implemented in a single unit, or be both physically and functionally distributed between different units and processors, paragraph 0126), and wherein the computer program product comprises instructions which, when executed on a processor of the data processing device, cause the following steps (i) through (iii) to be performed iteratively until a completion criterion is met which tests for the achievement of optimal patient- specific ventilation parameters θb,i = θb,opt (the optimal setting of remaining ventilator settings can be found through model simulation of clinical outcome variables and optimisation of settings according to for example a set of clinical preference functions (CPFs), or a rule set, paragraph 0105) and/or provides for the achievement of a predetermined number of iterations (possible to simulate for all plausible values of PEEP, either iteratively going through all possible values or by a numerical method searching through the PEEP values, thus locating the optimal PEEP value which can be advised to the clinician, paragraph 0105); i) Evaluation of the mechanical ventilation simulated on the lung model as a function of the ventilation parameter θb,i by determining the value of at least one patient-specific target function F=F(θb,i) from the lung model (model parameter of a physiological model as a function of the PEEP settings, control means may comprise one or more PEEP models, PEEP models allow use of physiological models to simulate effect of PEEP on the effect of changes in other mechanical ventilator settings by input to models of lung mechanics, paragraph 0060; PEEP models are inputted into model parameters which lead to outputs or outcome variables, Fig 3), wherein the target function F describes a lung reaction to the simulated mechanical ventilation as a function of at least one output parameter of the lung model (control means may comprise one or more PEEP models, PEEP models allow use of physiological models to simulate effect of PEEP on the effect of changes in other mechanical ventilator settings by input to models of lung mechanics, paragraph 0060; the PEEP models inputted would cause a lung reaction or response when inputted into the physiological models, Fig 3), ii) Evaluating the at least one determined value of the function F on the basis of at least one predetermined reference value (the optimal setting of remaining ventilator settings can be found through model simulation of clinical outcome variables and optimisation of settings according to for example a set of clinical preference functions (CPFs), or a rule set, paragraph 0105; a plurality of clinical preference functions (CPFs) relating settings of positive end expiratory pressure (PEEP) for the ventilation means to a corresponding set of clinical outcome variables to connect the decision support with clinical practise and experience, paragraph 0064; outcome variables are compared with clinical outcome variables that come from clinical practice and experience, Fig 3), and selecting at least one next ventilation parameter θb,next, using a selection method dependent on at least one previously used ventilation parameter θb,i (possible to simulate for all plausible values of PEEP, either iteratively going through all possible values or by a numerical method searching through the PEEP values, thus locating the optimal PEEP value which can be advised to the clinician, paragraph 0105; PEEP models may be adapted to the patient by a learning module, the learning module having a set of a priori settings of PEEP model parameters (MOD_P_PEEP) based on the currently measured model parameter (MOD_P) value of the corresponding physiological models (MOD), preferably based on a Bayesian distribution based on patient type and/or clinical condition, paragraph 0060; plausible values of PEEP are chosen iteratively, Fig 3; PEEP goes through a learning process, Fig 8) iii) Using the at least one next ventilation parameter θb,next as ventilation parameter θb,i to determine F=F(θb,i = θb,next) in step (i) (possible to simulate for all plausible values of PEEP, either iteratively going through all possible values or by a numerical method searching through the PEEP values, thus locating the optimal PEEP value which can be advised to the clinician, paragraph 0105; PEEP models may be adapted to the patient by a learning module, the learning module having a set of a priori settings of PEEP model parameters (MOD_P_PEEP) based on the currently measured model parameter (MOD_P) value of the corresponding physiological models (MOD), preferably based on a Bayesian distribution based on patient type and/or clinical condition, paragraph 0060; plausible values of PEEP are from repeated simulations of the physiological models, Fig 3; PEEP goes through a learning process, Fig 8).
It is noted that “achievement of patient-specific optimal ventilation parameters” is interpreted as actively achieving and operating the ventilator or device with the patient-specific optimal ventilation parameters.
Regarding Claim 25, Karbing discloses a ventilation machine (apparatus of Fig 2; the system comprising ventilation means 11 capable of mechanical ventilating said patient with air and/or one or more medical gases, paragraph 0097) comprising at least a control unit and a data processing device adapted to read and execute at least one computer program product (12, Fig 2; the ventilator means being controllable by said control means by operational connection thereto, control means integrated on a computer system, paragraph 0098; invention can be implemented by means of hardware, software, firmware or any combination of these, software running on one or more data processors and/or digital signal processors, paragraph 0125), and wherein the at least one data processing device is configured to provide data to the control unit for controlling the ventilation machine and/or to exchange data with the control unit for controlling ventilation of a patient (control means may be integrated on a computer system operationally connected to the ventilation means 11, paragraph 0098), wherein the computer program product uses a digital lung model (PEEP models allow use of physiological models to simulate effect of PEEP on the effect of changes in other mechanical ventilator settings by input to models of lung mechanics, paragraph 0060; invention or some of the features thereof can also be implemented as software running on one or more data processors and/or digital signal processors, paragraph 0125; invention may be implemented in a single unit, or be both physically and functionally distributed between different units and processors, paragraph 0126), and the computer program product comprises instructions which, when executed on a processor of the data processing device, cause the following steps (i) through (iii) to be performed iteratively until a completion criterion is met which tests for the achievement of optimal patient- specific ventilation parameters θb,i = θb,opt (the optimal setting of remaining ventilator settings can be found through model simulation of clinical outcome variables and optimisation of settings according to for example a set of clinical preference functions (CPFs), or a rule set, paragraph 0105) and/or provides for the achievement of a predetermined number of iterations (possible to simulate for all plausible values of PEEP, either iteratively going through all possible values or by a numerical method searching through the PEEP values, thus locating the optimal PEEP value which can be advised to the clinician, paragraph 0105); i) Evaluation of the mechanical ventilation simulated on the lung model as a function of the ventilation parameter θb,i by determining the value of at least one patient-specific target function F=F(θb,i) from the lung model (model parameter of a physiological model as a function of the PEEP settings, control means may comprise one or more PEEP models, PEEP models allow use of physiological models to simulate effect of PEEP on the effect of changes in other mechanical ventilator settings by input to models of lung mechanics, paragraph 0060; PEEP models are inputted into model parameters which lead to outputs or outcome variables, Fig 3), wherein the target function F describes a lung reaction to the simulated mechanical ventilation as a function of at least one output parameter of the lung model (control means may comprise one or more PEEP models, PEEP models allow use of physiological models to simulate effect of PEEP on the effect of changes in other mechanical ventilator settings by input to models of lung mechanics, paragraph 0060; the PEEP models inputted would cause a lung reaction or response when inputted into the physiological models, Fig 3), ii) Evaluating the at least one determined value of the function F on the basis of at least one predetermined reference value (the optimal setting of remaining ventilator settings can be found through model simulation of clinical outcome variables and optimisation of settings according to for example a set of clinical preference functions (CPFs), or a rule set, paragraph 0105; a plurality of clinical preference functions (CPFs) relating settings of positive end expiratory pressure (PEEP) for the ventilation means to a corresponding set of clinical outcome variables to connect the decision support with clinical practise and experience, paragraph 0064; outcome variables are compared with clinical outcome variables that come from clinical practice and experience, Fig 3), and selecting at least one next ventilation parameter θb,next, using a selection method dependent on at least one previously used ventilation parameter θb,i (possible to simulate for all plausible values of PEEP, either iteratively going through all possible values or by a numerical method searching through the PEEP values, thus locating the optimal PEEP value which can be advised to the clinician, paragraph 0105; PEEP models may be adapted to the patient by a learning module, the learning module having a set of a priori settings of PEEP model parameters (MOD_P_PEEP) based on the currently measured model parameter (MOD_P) value of the corresponding physiological models (MOD), preferably based on a Bayesian distribution based on patient type and/or clinical condition, paragraph 0060; plausible values of PEEP are chosen iteratively, Fig 3; PEEP goes through a learning process, Fig 8) iii) Using the at least one next ventilation parameter θb,next as ventilation parameter θb,i to determine F=F(θb,i = θb,next) in step (i) (possible to simulate for all plausible values of PEEP, either iteratively going through all possible values or by a numerical method searching through the PEEP values, thus locating the optimal PEEP value which can be advised to the clinician, paragraph 0105; PEEP models may be adapted to the patient by a learning module, the learning module having a set of a priori settings of PEEP model parameters (MOD_P_PEEP) based on the currently measured model parameter (MOD_P) value of the corresponding physiological models (MOD), preferably based on a Bayesian distribution based on patient type and/or clinical condition, paragraph 0060; plausible values of PEEP are from repeated simulations of the physiological models, Fig 3; PEEP goes through a learning process, Fig 8).
It is noted that “achievement of patient-specific optimal ventilation parameters” is interpreted as actively achieving and operating the ventilator or device with the patient-specific optimal ventilation parameters.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claim 19 is rejected under 35 U.S.C. 103 as being unpatentable over Karbing et al. (US 2017/0255756 A1) alone.
Regarding Claim 19, Karbing discloses the claimed invention of Claim 1. Karbing fails to explicitly disclose before the method is started, the patient- specific lung model is calibrated by means of a ventilation curve which contains either a pressure-time curve and/or a flow-time curve g, and/or a volume-time curve and/or respiratory gas mixture composition-time curve or curves of the patient derived therefrom, which comprises at least one breath of the patient.
However, Karbing teaches a physiological model covering any means for linking clinically measurable values mathematically and for the individual patient, that is, that any parameters that needs tuning for the model to describe the individual patient's physiology should be possible to estimate from clinical measurements and clinical measurable values can include pressure and volume with lung compliance (paragraph 0025). Karbing also teaches data may particularly be described as data originating from other sources than the mechanical ventilator itself (this could be sensor, blood gases, doctor input etc.) (paragraph 0101) and data could be estimated or guessed values being indicative of the respiratory feedback in the blood of said patient, preferably based on the medical history and/or present condition of the said patient (paragraph 0102). Karbing further teaches the use of measurement means for measuring the inspired gas and/or respiratory feedback (paragraph 0099), the data provided by the measurement means can be used in one or more physiological models (paragraph 0100), and the changes patient physiological variables being measured by measurement means which assesses ventilation, flow, pressure and volumes, and/or inspired and expired contents of O2 and CO2, and/or blood gas contents (O2 and CO2) and/or changes in acid base status of blood (paragraph 0109).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to calibrate or tune the lung model to be specific to the patient via measurements of pressure, flow, or volume that are tied with the patient’s breath, as taught by Karbing, since it is known to utilize clinical measurements and condition of the patient to modify the lung model to more accurately simulate the individual patient’s lungs. Karbing shows that one of ordinary skill in the art would be capable of tuning or modifying the lung model to suit the patient’s needs and constraints based on clinical measurements. These clinical measurements are obviously shown to be obtained through measurement means found on the patient and would include measurements of pressure, flow, volume, and inspired and expired contents of O2 and CO2 or mixtures of the two. Additionally, it would be obvious for one of ordinary skill in the art to require some form of calibration or tuning with the lung model before a treatment is provided as each individual patient would have distinct needs and requirements. It is noted that the curves are interpreted as merely measurements or data points of pressure, flow, volume, or other measured ventilation parameters since there is nothing in the claim that indicates these curves need to be visually depicted.
Claim 20 is rejected under 35 U.S.C. 103 as being unpatentable over Karbing et al. (US 2017/0255756 A1) in view of Banner et al. (US 2014/0276173 A1).
Regarding Claim 20, Karbing teaches the claimed invention of Claim 19. Karbing also teaches the use of measurement means for measuring the inspired gas and/or respiratory feedback (paragraph 0099), the data provided by the measurement means can be used in one or more physiological models (paragraph 0100), and the changes patient physiological variables being measured by measurement means which assesses ventilation, flow, pressure and volumes, and/or inspired and expired contents of O2 and CO2, and/or blood gas contents (O2 and CO2) and/or changes in acid base status of blood (paragraph 0109).
Karbing fails to teach the parameterized pressure-time curve maps the patient-specific pressure in the trachea of the patient-specific lung model.
However, Banner, of the same field of endeavor, teaches methods for non-invasively and accurately estimating and monitoring resistance and work of breathing parameters from airway pressure and flow sensors attached to the ventilator-dependent patient using an adaptive mathematical model (Abstract) including the parameterized pressure-time curve maps the patient-specific pressure in the trachea of the patient-specific lung model ((a) receiving patient respiratory data, including tracheal pressure data, which may be obtained from an intra-tracheal pressure sensing apparatus, a cuff pressure system, or similar tracheal pressure estimation; (b) calculating respiratory parameters from the patient's respiratory data; (c) inputting the tracheal pressure data and necessary respiratory parameters into a mathematical model for determining R.sub.ETT and R.sub.TOT, paragraph 0065; the tracheal pressure sensing device 100 can be stored in the memory of the microprocessor at user-defined rates for as-needed retrieval and analysis, tracheal pressure sensors 90, 95, 100 may continually monitor/sense the flow rate and the pressure of the breathing gas 32 proximate the respective sensors, paragraph 0111) since tracheal pressure is a known measured value that is used in a mathematical model for ventilation (paragraph 0022).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the measurement means to include measurements of the tracheal pressure, as taught by Banner, since tracheal pressure is a known measured value that is used in a mathematical model for ventilation (Banner: paragraph 0022). Since Karbing already teaches about tuning the lung model to fit the individual patient’s needs with clinical measurements, Banner merely further elaborates on the particular measurements involved which would include tracheal pressure.
Claims 3-4 are rejected under 35 U.S.C. 103 as being unpatentable over Karbing et al. (US 2017/0255756 A1) in view of Wynden et al. (WO 2013036677 A1).
Regarding Claim 3, Karbing discloses the claimed invention of Claim 1. Karbing also discloses the selection method for selecting at least one next ventilation parameter θb,next includes an algorithm, in particular an optimization method according to Bayes (PEEP models may be adapted to the patient by a learning module, the learning module having a set of a priori settings of PEEP model parameters (MOD_P_PEEP) based on the currently measured model parameter (MOD_P) value of the corresponding physiological models (MOD), preferably based on a Bayesian distribution based on patient type and/or clinical condition, paragraph 0060; present invention may include a Bayesian or similar learning methods where model parameters used for calculating decision support are stepwise learned where values at previous steps are taken into account when learning the current value, paragraph 0019).
Karbing fails to explicitly disclose the algorithm is implemented in particular using one or more Gaussian processes, random Forrests, artificial neural networks or other regression models, a fuzzy logic algorithm, an algorithm based on an evolutionary method, an algorithm including a gradient method, and/or an algorithm based on stochastic techniques.
However, Wynden, reasonably pertinent to the problem of utilizing machine learning techniques to analyze signal data relative to clinical data, teaches systems and methods for aggregating, managing, and/or analyzing data (Abstract) including the algorithm is implemented in particular using one or more Gaussian processes (Bayesian statistics, Naive Bayes classifier, Bayesian network, Bayesian knowledge base, dynamic Bayesian networks, Gaussian process regression, paragraph 0078), random Forrests (Random Forests, paragraph 0078), artificial neural networks (artificial neural network, paragraph 0078) or other regression models (regression analysis, logistic regression, paragraph 0078), a fuzzy logic algorithm (information fuzzy networks, fuzzy clustering, paragraph 0078) since these are known machine learning approaches for analyzing signal data relative to clinical data (paragraph 0078).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the selection method to utilize these listed types of machine learning, as taught by Wynden, since these are known machine learning approaches for analyzing signal data relative to clinical data (Wynden: paragraph 0078). These various machine learning techniques are known to one of ordinary skill in the art and would be utilized for the analysis of the PEEP data in relation to the clinical data to ensure the ventilation parameters are optimized.
Regarding Claim 4, Karbing discloses the claimed invention of Claim 1. Karbing also discloses the device may include a Bayesian or similar learning methods where model parameters used for calculating decision support are stepwise learned where values at previous steps are taken into account when learning the current value (paragraph 0019). Karbing fails to explicitly disclose the selection method includes an acquisition function for selecting at least one next ventilation parameter θb,next using a probabilistic regression method which depends on at least one previously determined data set Ti = (θb,i , F(θb,i)), in particular a regression method for a Gaussian process.
However, Wynden, reasonably pertinent to the problem of utilizing machine learning techniques to analyze signal data relative to clinical data, teaches systems and methods for aggregating, managing, and/or analyzing data (Abstract) including using a probabilistic regression method which depends on at least one previously determined data set (analyze the signal data relative to the clinical data, paragraph 0078; clinical data would be considered a previously determined data set), in particular a regression method for a Gaussian process (Gaussian process regression, paragraph 0078) since these are known machine learning approaches for analyzing signal data relative to clinical data (paragraph 0078).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the selection method to utilize Gaussian process regression, as taught by Wynden, since these are known machine learning approaches for analyzing signal data relative to clinical data (Wynden: paragraph 0078). The Gaussian process regression technique is a known machine learning technique that one of ordinary skill in the art would utilize for analysis and selection of the PEEP data in relation to the clinical data to ensure the ventilation parameters are optimized.
Claims 5-6 are rejected under 35 U.S.C. 103 as being unpatentable over Karbing et al. (US 2017/0255756 A1) in view of Hirsch et al. (US 2019/0096526 A1).
In the alternative, Regarding Claim 5, Karbing discloses the claimed invention of Claim 1. Karbing also discloses the device may include a Bayesian or similar learning methods where model parameters used for calculating decision support are stepwise learned where values at previous steps are taken into account when learning the current value (paragraph 0019). Karbing fails to explicitly disclose the selection method for selecting at least one next ventilation parameter θb,next includes an acquisition function which uses the expected value of the improvement, in particular taking into account constraints.
However, Hirsch, reasonably pertinent to the problem of utilizing acquisition functions for Bayesian methods, teaches a method and apparatus for transmitting recommendation of a health diagnosis and treatment of a patient (Abstract) including an acquisition function which uses the expected value of the improvement, in particular taking into account constraints (Probability of Improvement, Expected Improvement, paragraph 0153; learning algorithms must inherently take into account constraints or rules to optimize properly) since this is a known acquisition function used with the framework of Bayesian decisions (paragraph 0153).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the existing Bayesian learning method to utilize expected improvement functions, as taught by Hirsch, since this is a known acquisition function used with the framework of Bayesian decisions (Hirsch: paragraph 0153).
Regarding Claim 6, Karbing discloses the claimed invention of Claim 1. Karbing also discloses the device may include a Bayesian or similar learning methods where model parameters used for calculating decision support are stepwise learned where values at previous steps are taken into account when learning the current value (paragraph 0019). Karbing fails to explicitly disclose the selection method for selecting at least one next ventilation parameter θb,next includes an acquisition function which uses an entropy search, or which uses a knowledge gradient.
However, Hirsch, reasonably pertinent to the problem of utilizing acquisition functions for Bayesian methods, teaches a method and apparatus for transmitting recommendation of a health diagnosis and treatment of a patient (Abstract) including an acquisition function which uses an entropy search (entropy search, paragraph 0153) since this is a known acquisition function used with the framework of Bayesian decisions (paragraph 0153).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the existing Bayesian learning method to utilize entropy searches, as taught by Hirsch, since this is a known acquisition function used with the framework of Bayesian decisions (Hirsch: paragraph 0153).
Claim 13 is rejected under 35 U.S.C. 103 as being unpatentable over Karbing et al. (US 2017/0255756 A1) in view of Brooks et al. (US 2022/0189632 A1).
Regarding Claim 13, Karbing discloses the claimed invention of Claim 1. Karbing also discloses the device may include a Bayesian or similar learning methods where model parameters used for calculating decision support are stepwise learned where values at previous steps are taken into account when learning the current value (paragraph 0019). Karbing fails to explicitly disclose in step (iii) the ventilation parameter values θb,i are varied stochastically.
However, Brooks, reasonably pertinent to the problem of optimization of parameters, teaches methods for selecting settings for a treatment of the patient (Abstract) including the parameters are varied stochastically (for each of set of internal parameters that the system varies while controlling the environment, the system can vary the values by stochastically sampling values to optimize a figure of merit for the internal parameter, paragraph 0115; any sets of internal parameters that are varied by stochastically sampling, the system maintains parameters that define a range of possible values for the internal parameter and maintains a causal model that identifies causal relationships between the possible values for the internal parameter and a figure of merit for the internal parameter, paragraph 0117; system can then determine whether the clustering parameters need to be adjusted (step 710), i.e., determines if the current values of the clustering parameters are not optimal and, if so, updates the clustering parameters for the controllable element, system can accomplish this by adjusting the values using heuristics, using stochastic sampling, or both heuristics and stochastic sampling, paragraph 0232) since this is a known technique of parameter optimization (paragraph 0232).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to vary the parameters stochastically, as taught by Brooks, since this is a known technique of parameter optimization (Brooks: paragraph 0232).
Claim 14 is rejected under 35 U.S.C. 103 as being unpatentable over Karbing et al. (US 2017/0255756 A1) in view of Seely et al. (US 2017/0071549 A1).
Regarding Claim 14, Karbing discloses the claimed invention of Claim 1. Karbing also discloses the device may include a Bayesian or similar learning methods where model parameters used for calculating decision support are stepwise learned where values at previous steps are taken into account when learning the current value (paragraph 0019). Karbing further discloses a plurality of clinical preference functions (CPFs) relating settings of positive end expiratory pressure (PEEP) for the ventilation means to a corresponding set of clinical outcome variables to connect the decision support with clinical practice and experience (paragraph 0064). Karbing fails to explicitly disclose a set of initial input respiration parameter values θb,init,1:J is produced by means of a random or quasi-random method, in particular Monte-Carlo or Latin hyper-cube sampling.
However, Seely, reasonably pertinent to the problem of conveying clinically relevant information and utilizing previously collected data, teaches a system and method to estimate the probability of a patient’s death (Abstract) including a set of input parameter values is produced by means of a random or quasi-random method, in particular Monte-Carlo sampling (indices for conveying the clinically relevant information, for a new patient, can be based on statistical models created using previously collected data from patients, clinically relevant variables used by the models are selected through optimization methods such as Monte-Carlo methods, cross-validation procedures are used in combination with optimization methods for the identification of the models and their parameters, paragraph 0044) since this is a known technique of extracting clinically relevant data and parameters for optimization purposes and is known to be used with models like Bayesian classifiers (paragraph 0044).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the selection of input parameters to utilize Monte-Carlo methods, as taught by Seely, since this is a known technique of extracting clinically relevant data and parameters for optimization purposes and is known to be used with models like Bayesian classifiers (Seely: paragraph 0044).
Claims 15-16 are rejected under 35 U.S.C. 103 as being unpatentable over Karbing et al. (US 2017/0255756 A1) and Seely et al. (US 2017/0071549 A1) as applied to Claim 14, and in further view of Wynden et al. (WO 2013036677 A1).
Regarding Claim 15, Karbing-Seely combination teaches the claimed invention of Claim 14. Karbing-Seely combination also teaches, in step (ii), the function values of function B which have been calculated from the at least one output parameter by simulating the set of initial input respiration parameter values θb,init,1:J are used for training (Karbing: may include a Bayesian or similar learning methods where model parameters used for calculating decision support are stepwise learned where values at previous steps are taken into account when learning the current value, paragraph 0019), wherein B describes a mechanical loading of the lung as a function of at least one output parameter of the lung model, wherein the at least one output parameter describes a mechanical loading value of the lung of the patient (Karbing: model parameter of a physiological model as a function of the PEEP settings, control means may comprise one or more PEEP models, PEEP models allow use of physiological models to simulate effect of PEEP on the effect of changes in other mechanical ventilator settings by input to models of lung mechanics, paragraph 0060; lung mechanics outcome variables listed, paragraph 0048; the lung mechanics outcome variables are tied with the mechanical loading or functioning of the lung).
Karbing-Seely combination fails to explicitly teach training a Gaussian process.
However, Wynden, reasonably pertinent to the problem of utilizing machine learning techniques to analyze signal data relative to clinical data, teaches systems and methods for aggregating, managing, and/or analyzing data (Abstract) including training a Gaussian process (analyze the signal data relative to the clinical data, Gaussian process regression, paragraph 0078; components of the plugin include the algorithms with which to process the data, parameters of the algorithms, training data from machine or statistical learning algorithms, as well as rules to manage the application of the various algorithms or to provide expert system functionality, paragraph 00108) since these are known machine learning approaches for analyzing signal data relative to clinical data (paragraph 0078).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to train the method with Gaussian process regression, as taught by Wynden, since these are known machine learning approaches for analyzing signal data relative to clinical data (Wynden: paragraph 0078). The Gaussian process regression technique is a known machine learning technique that one of ordinary skill in the art would utilize for analysis and training of the PEEP data in relation to the clinical data to ensure the ventilation parameters are optimized.
Regarding Claim 16, Karbing-Seely-Wynden combination teaches the claimed invention of Claim 15. Karbing-Seely-Wynden combination also teaches in step (ii), the function values of function B which have been calculated from the at least one output parameter by simulating the set of next input respiration parameter values θb,init,1:J are used for further training of the Gaussian process (Karbing: may include a Bayesian or similar learning methods where model parameters used for calculating decision support are stepwise learned where values at previous steps are taken into account when learning the current value, paragraph 0019; possible to simulate for all plausible values of PEEP, either iteratively going through all possible values or by a numerical method searching through the PEEP values, thus locating the optimal PEEP value which can be advised to the clinician, paragraph 0105; Wynden: analyze the signal data relative to the clinical data, Gaussian process regression, paragraph 0078; components of the plugin include the algorithms with which to process the data, parameters of the algorithms, training data from machine or statistical learning algorithms, as well as rules to manage the application of the various algorithms or to provide expert system functionality, paragraph 00108; the combination device would merely repeat the training process to obviously further optimize the parameters), wherein B describes a mechanical loading of the lung as a function of at least one output parameter of the lung model, wherein the at least one output parameter describes a mechanical loading value of the lung of the patient (Karbing: model parameter of a physiological model as a function of the PEEP settings, control means may comprise one or more PEEP models, PEEP models allow use of physiological models to simulate effect of PEEP on the effect of changes in other mechanical ventilator settings by input to models of lung mechanics, paragraph 0060; lung mechanics outcome variables listed, paragraph 0048; the lung mechanics outcome variables are tied with the mechanical loading or functioning of the lung).
Claim 17 is rejected under 35 U.S.C. 103 as being unpatentable over Karbing et al. (US 2017/0255756 A1), Seely et al. (US 2017/0071549 A1), and Wynden et al. (WO 2013036677 A1) as applied to Claim 15, and in further view of Hirsch et al. (US 2019/0096526 A1) and Dubois et al. (US 2020/0303080 A1).
Regarding Claim 17, Karbing-Seely-Wynden combination teaches the claimed invention of Claim 15. Karbing-Seely-Wynden combination also teaches wherein N describes the enrichment of gas in the blood of the lung as a function of at least one output parameter of the lung model (Karbing: PEEP models then in turn allow use of physiological models to simulate the effect of PEEP on the effect of changes in other mechanical ventilator settings by input to models of for example gas exchange, paragraph 0060), wherein the at least one output parameter describes a gas partial pressure in the blood of the patient (Karbing: gas exchange outcome variables include oxygen partial pressure and carbon dioxide partial pressure, paragraph 0050; control means may further comprise a plurality of clinical preference functions (CPFs) relating settings of positive end expiratory pressure (PEEP) for the ventilation means to a corresponding set of clinical outcome variables to connect the decision support with clinical practise and experience, paragraph 0064), and/or B describes a mechanical loading of the lung as a function of at least one output parameter of the lung model, wherein the at least one output parameter describes a mechanical loading value of the lung of the patient (Karbing: model parameter of a physiological model as a function of the PEEP settings, control means may comprise one or more PEEP models, PEEP models allow use of physiological models to simulate effect of PEEP on the effect of changes in other mechanical ventilator settings by input to models of lung mechanics, paragraph 0060; lung mechanics outcome variables listed, paragraph 0048; the lung mechanics outcome variables are tied with the mechanical loading or functioning of the lung).
The current Karbing-Seely-Wynden combination does not explicitly teach in step (ii), the selection function is an acquisition function, which calculates next ventilation parameter values θb,next taking into account the following: I(θb,next ) = Δ (θb,next-) * max {0,B(θb+) Δ(θb,next ) where B(θb+) represents the function value with the so far lowest mechanical load as a function of the ventilation parameter θb+- which has been most suitable so far, and wherein the indicator function is 1 if the function N(θb,next) is less than or greater than a predetermined reference value, and zero otherwise.
However, Karbing further teaches the device is capable of determining if N(θb,next) is less than, equal to, or greater than a predetermined reference value (PEEP models then in turn allow use of physiological models to simulate the effect of PEEP on the effect of changes in other mechanical ventilator settings by input to models of for example gas exchange, paragraph 0060; at least two, three, four, or five, physiological models are integrated by having one, or more, variables in common, outcome variables may be used in several physiological models of the present invention enabling a close integration of the physiological models, paragraph 0062; PEEP models 20 then allow use of physiological models to simulate the effect of PEEP on the effect of changes in other mechanical ventilator settings by input to models of for example gas exchange, the optimal setting of remaining ventilator settings can be found through model simulation of clinical outcome variables and optimisation of settings according to for example a set of clinical preference functions (CPFs), or a rule set, paragraph 0105) since it is known to compare gas exchange outcome variables with pre-existing clinical values to determine if the partial pressures are optimized in relation to the ventilator settings involved.
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to compare gas exchange outcome variables with pre-existing clinical values, as taught by Karbing, since it is known to compare gas exchange outcome variables with pre-existing clinical values to determine if the partial pressures are optimized in relation to the ventilator settings involved. Karbing utilizes various models including the combination of lung mechanics and gas exchange models to fully optimize the PEEP settings involved in a ventilator. Karbing takes into consideration all of the parameters of the models and compares them to clinical preference functions or existing clinical values to further optimize the settings of the device.
Though Karbing-Seely-Wynden combination does not explicitly teach an indicator function in which 1 is used to indicate function N(θb,next) is less than or greater than a predetermined reference value and zero is used otherwise, this would be an obvious design choice for one of ordinary skill in the art as it would merely be a known comparison technique in an algorithm. Thus, one of ordinary skill in the art would obviously modify the algorithm to utilize 1 and 0 as a way to label whether or not a gas exchange outcome variable is the same or different from a pre-existing clinical value. It is noted that Applicant has not provided any claim limitations that ties the indicator function with the acquisition function mentioned earlier in the claim. Applicant has also provided any details on how the indicator function is taken into account.
Karbing-Seely-Wynden combination teaches the device may include a Bayesian or similar learning methods where model parameters used for calculating decision support are stepwise learned where values at previous steps are taken into account when learning the current value (Karbing: paragraph 0019).
Karbing-Seely-Wynden combination does not explicitly teach in step (ii), the selection function is an acquisition function, which calculates next ventilation parameter values θb,next taking into account the following: I(θb,next ) = Δ (θb,next-) * max {0,B(θb+) Δ(θb,next ) where B(θb+) represents the function value with the so far lowest mechanical load as a function of the ventilation parameter θb+- which has been most suitable so far.
However, Hirsch, reasonably pertinent to the problem of utilizing acquisition functions for Bayesian methods, teaches a method and apparatus for transmitting recommendation of a health diagnosis and treatment of a patient (Abstract) including an acquisition function, which uses expected improvement (Probability of Improvement, Expected Improvement, paragraph 0153; learning algorithms must inherently take into account constraints or rules to optimize properly) since this is a known acquisition function used with the framework of Bayesian decisions (paragraph 0153). It is noted that Applicant admitted the acquisition function and equation being claimed is an expected improvement function that is part of Bayesian optimization (Specification: Page 31).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the existing Bayesian learning method to utilize expected improvement functions, as taught by Hirsch, since this is a known acquisition function used with the framework of Bayesian decisions (Hirsch: paragraph 0153). Since Karbing already teaches that a Bayesian learning method can be used to optimize ventilation parameters, one of ordinary skill in the art would be capable of utilizing acquisition functions tied with Bayesian optimization, including Expected Improvement, to further optimize these parameters.
Karbing-Seely-Wynden-Hirsch combination does not explicitly teach B(θb+) represents the function value with the so far lowest mechanical load as a function of the ventilation parameter θb+- which has been most suitable so far.
However, Dubois, reasonably pertinent to the problem of simulating lung models, teaches a method for simulating respiratory dynamics of a virtual lung (Abstract) including B(θb+) represents the function value with the so far lowest mechanical load as a function of the ventilation parameter θb+- which has been most suitable so far (PPEP represents the minimum air pressure imposed by a virtual ventilator at the input of the respiratory system, input of the virtual lung, this pressure may be parameterized in order to provide an air to respiration for certain patients in order to ensure minimum pressure in respiratory cycle, paragraph 0124) since this is a known parameter taken into account for virtual lungs or lung models (paragraph 0124).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to utilize the lowest mechanical load or pressure on a virtual lung in optimization methods, as taught by Dubois, since this is a known parameter taken into account for virtual lungs or lung models (Dubois: paragraph 0124).
Claim 18 is rejected under 35 U.S.C. 103 as being unpatentable over Karbing et al. (US 2017/0255756 A1) in view of De Backer (US 2012/0072193 A1).
Regarding Claim 18, Karbing discloses the claimed invention of Claim 1. Karbing fails to disclose the patient-specific lung model is produced as a function of measured image data of the lung of the patient.
However, De Backer, of the same field of endeavor, teaches a method for determining optimized parameters for mechanical ventilation of a subject (Abstract) including the patient-specific lung model is produced as a function of measured image data of the lung of the patient (according to the embodiment, a CT scan of the thorax of the subject is taken 2, resulting in scan data 12, from the scan data 12, a patient specific lung model is generated 4, resulting in data concerning the geometry of the airways, paragraph 0043; data concerning three-dimensional images of the respiratory system of the subject is obtained, the images may have been previously acquired using any method of the art, methods include magnetic resonance imaging, positron emission tomography and computer tomography (CT) imaging, paragraph 0047; device performs flow and/or structural simulations at different pressure settings, mass flow rate distribution is monitored and the optimal parameters are selected for the patient, paragraph 0063) to provide optimization of the setting of parameters for mechanical ventilation (paragraph 0008).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to utilize image data of the lung of the patient for the lung models, as taught by De Backer, to provide optimization of the setting of parameters for mechanical ventilation (De Backer: paragraph 0008). This would provide further accuracy in the lung models and tune the models towards individual patients for more personalized parameters.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to BRIAN THAI-BINH KHONG whose telephone number is (571)272-1857. The examiner can normally be reached Monday to Thursday 9:00 am-6:00 pm.
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, Kendra Carter can be reached at (571) 272-9034. 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.
/BRIAN T KHONG/Examiner, Art Unit 3785
/JOSEPH D. BOECKER/Primary Examiner, Art Unit 3785
Prosecution Insights