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 .
Drawings
The drawings are objected to under 37 CFR 1.83(a). The drawings must show every feature of the invention specified in the claims. Therefore, the input and output variables must be shown or the feature(s) canceled from the claim(s). All figures with graphs in the present application display the same data line with no variation between, for example, a graph labeled to represent the estimated target value and a graph labeled to represent the predicted target value, ergo not showing the claimed features. No new matter should be entered.
The drawings are objected to because no axes are labeled in any of the figures, resulting in lack of clarity on what the figure is displaying. The legend in all graphs, except for in Fig. 2B, labels the displayed line of data to be “Input,” not aligning with the specification on what each graph is meant to display.
Corrected drawing sheets in compliance with 37 CFR 1.121(d) are required in reply to the Office action to avoid abandonment of the application. Any amended replacement drawing sheet should include all of the figures appearing on the immediate prior version of the sheet, even if only one figure is being amended. The figure or figure number of an amended drawing should not be labeled as “amended.” If a drawing figure is to be canceled, the appropriate figure must be removed from the replacement sheet, and where necessary, the remaining figures must be renumbered and appropriate changes made to the brief description of the several views of the drawings for consistency. Additional replacement sheets may be necessary to show the renumbering of the remaining figures. Each drawing sheet submitted after the filing date of an application must be labeled in the top margin as either “Replacement Sheet” or “New Sheet” pursuant to 37 CFR 1.121(d). If the changes are not accepted by the examiner, the applicant will be notified and informed of any required corrective action in the next Office action. The objection to the drawings will not be held in abeyance.
Claim Objections
Claim 14 is objected to because of the following informalities: “learning module” should be “learning model”. Appropriate correction is required.
Claim Rejections - 35 USC § 112a
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claims 1-19 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the enablement requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to enable one skilled in the art to which it pertains, or with which it is most nearly connected, to make and/or use the invention.
There are many factors to be considered when determining whether there is sufficient evidence to support a determination that a disclosure does not satisfy the enablement requirement and whether any necessary experimentation is "undue." In re Wands, 858 F.2d 731, 737, 8 USPQ2d 1400, 1404 (Fed. Cir. 1988). These factors include, but are not limited to:
The breadth of the claims;
The nature of the invention;
The state of the prior art;
The level of one of ordinary skill;
The level of predictability in the art;
The amount of direction provided by the inventor;
The existence of working examples; and
The quantity of experimentation needed to make or use the invention based on the content of the disclosure.
The standard for determining whether the specification meets the enablement test was first stated in Mineral Separation v. Hyde, 242 U.S. 261, 270 (1916), and asks if the experimentation needed to practice the invention undue or unreasonable.
The claimed invention is enabled if any person skilled in the art can make and use the invention without undue experimentation. The focus is on ‘undue’ rather than on ‘experimentation’ (In re Wands, at 737, 8 USPQ2d at 1404; see also United States v. Telectronics, Inc., 857 F.2d 778, 785, 8 USPQ2d 1217, 1223 (Fed. Cir. 1988)).
A patent need not teach what is well known in the art (In re Buchner, 929 F.2d 660, at 661, 18 USPQ2d 1331, at 1332 (Fed. Cir. 1991); Hybritech, Inc. v. Monoclonal Antibodies, Inc., 802 F.2d 1367, 1384, at 231 USPQ 81, at 94 (Fed. Cir. 1986), cert. denied, 480 U.S. 947 (1987); Lindemann Maschinenfabrik GMBH v. American Hoist & Derrick Co., 730 F.2d 1452, at 1463, 221 USPQ 481, at 489 (Fed. Cir. 1984)).
Determining whether claims are sufficiently enabled by the specification is based on underlying findings of fact. In re Vaeck, 947 F.2d 488, at 495, 20 USPQ2d 1438, at 1444 (Fed. Cir. 1991); Atlas Powder Co. v. E.I. du Pont de Nemours & Co., 750 F.2d 1569, at 576, 224 USPQ 409, at 413 (Fed. Cir. 1984).
The Breadth of the Claims
The claims are overly broad because the claims encompass a method and apparatus for using photoplethysmography (PPG) data and a learning model to output an estimated target value of the arterial blood pressure in a current time section and a predicted target value of the arterial blood pressure after the current time section without any detail of how the training is executed or how the model processes the PPG data to output the estimated and predicted values based on time sections.
The Amount of Direction and the Existence of Working Examples
The inventor discloses in paragraphs [0044-0045] that a pre-constructed, predetermined deep learning model is trained by setting PPG as an input variable, incorporating noise into the input variable, and setting the estimated target value as an output. Subsequently, [0046] describes inputting the PPG based on the learning model and then performing the deep learning to output the estimated target value. Similarly, [0055] describes inputting the PPG and the estimated target value of the arterial blood pressure based on the trained learning model and then performing the deep learning to predict the predicted target value of the arterial blood pressure. No further steps are described for the construction of the deep learning model, how the training is executed (beyond generically setting inputs/outputs), or how the model processes the PPG data to output the estimated and predicted values based on time sections (beyond the generically mentioned use of deep learning techniques).
The inventor provides no working examples of this technology. Since the inventor provides no guidance, a person of ordinary skill in the art would need to refer to prior art.
The Quantity of Experimentation Needed to Make or Use the Invention
No algorithm or steps involved in the methods of constructing, training, or executing the deep learning model are described beyond generic setting of inputs/outputs and use of deep learning. It is clear that one of ordinary skill in the art endeavoring to make and use the claimed invention could not do so without undue experimentation, and the claims thus fail the enablement requirement of 35 U.S.C. 112(a).
Claim Rejections - 35 USC § 112b
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 1-19 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.
Regarding claims 1, the claim recites the limitation “training a predetermined learning model that is pre-constructed by setting the sensed photoplethysmography as an input variable and setting an estimated target value of the arterial blood pressure in a current time section and a predicted target value of the arterial blood pressure after the current time section as an output variable.” No algorithm or steps involved in the methods of processing are described beyond the generic mention of “deep learning.” The lack of specificity leads to an interpretation within the claims that any method that uses any kind of deep learning for the learning model is encompassed in the invention. The scope is too broad, as no steps or processes are outlined in relation to how these methods analyze the data inputted into them. There is no information as to how the generic deep learning model takes the input PPG and estimates/predicts the target values of the arterial blood pressure from the deep learning model. The limitation does not satisfy the written description requirement as the scope is too broad, with no specific steps or methods outlined in the specification. Further regarding claims 1, it is unclear whether both “an estimated target value of the arterial blood pressure in a current time section” and “a predicted target value of the arterial blood pressure after the current time section” are to be set as output variables as “output variable” is singular. Moreover, the limitation “outputting… by inputting the photoplethysmography based on the learning model and then performing the deep learning,” is unclear as to whether the inputs are derived from the learning model or put into the learning model as well as whether the deep learning occurs prior to or after the outputting of a target value. Claims 2-10 are also rejected due to their dependency on claim 1.
Claims 3-6 claims have the same issues as claim 1 in the limitation “outputting… by inputting the photoplethysmography based on the learning model and then performing the deep learning,” being unclear as to whether the inputs are derived from the learning model or put into the learning model as well as whether the deep learning occurs prior to or after the outputting of a target value.
Regarding claim 11, the claim recites the limitation “trains a learning model by setting the photoplethysmography provided from the sensing device as an input variable of a predetermined learning model that is pre-constructed and setting an estimated target value of the arterial blood pressure in a current time section and a predicted target value of the arterial blood pressure after the current time section as an output variable and which outputs the estimated target value or the predicted target value of the arterial blood pressure by performing deep learning on the photoplethysmography based on the learning model.” No algorithm or steps involved in the methods of processing are described beyond the generic mention of “deep learning.” The lack of specificity leads to an interpretation within the claims that any method that uses any kind of deep learning for the learning model is encompassed in the invention. The scope is too broad, as no steps or processes are outlined in relation to how these methods analyze the data inputted into them. There is no information as to how the generic deep learning model takes the input PPG and estimates/predicts the target values of the arterial blood pressure from the deep learning model. The limitation does not satisfy the written description requirement as the scope is too broad, with no specific steps or methods outlined in the specification. Further regarding claim 11, it is unclear whether both “an estimated target value of the arterial blood pressure in a current time section” and “a predicted target value of the arterial blood pressure after the current time section” are to be set as output variables as “output variable” is singular. Claims 12-19 are also rejected due to their dependency on claim and 11.
Regarding claim 14, the limitation “the photoplethysmography and a measurement value of the arterial blood pressure or the actual measurement value of the arterial blood pressure are input based on the learning model” is unclear as to whether the inputs are derived from the learning model or put into the learning model. It is also unclear whether “a measurement value of the arterial blood pressure” and “the actual measurement value of the arterial blood pressure” are the same or different. By virtue of dependency, claim 15 is also rejected.
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.
Claim(s) 1, 4, 6-8, 11, 14, and 16-17 is/are rejected under 35 U.S.C. 103 as being unpatentable over Ripoll (US 20130012823 A1) in view of Mulligan (US 20150065826 A1).
Regarding claim 1, Ripoll teaches a method of estimating arterial blood pressure based on deep learning executed by a computer ([0041] “FIG. 3 is a flow diagram of a method 300 of using PPG pulse shape measurements and patient statistics to determine the blood pressure of a patient in a non-invasive manner.”), the method comprising:
sensing photoplethysmography from a predetermined body part ([0043] “At block 320, an electronic PPG signal is captured from a measurement location on a patient. The measurement location may be, for example and without limitation, a finger or an ear lobe.”);
training a predetermined learning model that is pre-constructed by setting the sensed photoplethysmography as an input variable and setting an estimated target value of the arterial blood pressure in a current time section as an output variable ([0038] “The estimator function system 240 may work blindly, in the sense that no functional restriction is imposed on the relationship between pulse shapes and blood pressure. Because the functional form relating the PPG pulse and the blood pressure level is unknown, embodiments employ techniques to infer a robust function when presented with input variables obtained by PPG pulse system 210 and clinical parameters system 220, while ignoring irrelevant parameters derived from the PPG pulse. Embodiments may use a machine learning algorithm, such as a "random forest", deep belief network trained using restricted Boltzmann machines, or support vector machine.” [0039] “In order to estimate blood pressure in accordance with certain embodiments, machine learning algorithms may require a training phase. Training may be performed only once, and no calibration or customization may be needed in the future. The training phase may include obtaining a database containing clinical information of a set of patients, including gender, weight, height, age, and other clinical parameters. Additionally, PPG pulse measurements for these patients are obtained, along with blood pressure values for the patients in the set. This information may be used to train the machine learning algorithm by minimizing errors and estimating the parameters of the machine learning algorithm”).
However, Ripoll fails to disclose outputting a predicted blood pressure value for after the current time section. Mulligan teaches tools and techniques for estimating and/or predicting a patient's current and/or future blood pressure. Mulligan discloses and a predicted target value of the arterial blood pressure after the current time section as an output variable ([0047] “G. Displaying an estimate and/or prediction of a patients current and/or future blood pressure status.” [0094] “At block 230, the method 200 can include predicting a patient's future blood pressure. Similar to the estimate of the patient's current blood pressure, the prediction of the patient's future blood pressure is based on analysis of the monitored sensor data (either analysis of the monitored data itself, analysis of parameters derived from the monitored data, such as CRI, or both). A number of different predictions can be made by various embodiments, again depending on the types of models generated to analyze the data. For instance, embodiments can predict when a patient's blood pressure will increase or decrease to a specified value. Alternatively and/or additionally, embodiments can predict when a patient's blood pressure will increase or decrease by a specified amount.”).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Ripoll to include a predicted target value of the arterial blood pressure after the current time section as an output variable as disclosed in Mulligan to further help a patient or clinician better monitor blood pressure and a patent's response to treatment or degrading/improving health on an acute or a chronic basis (Mulligan [0092, 0098]).
The combination of Ripoll/Mulligan discloses and outputting the estimated target value or the predicted target value of the arterial blood pressure by inputting the photoplethysmography based on the learning model and then performing the deep learning (Ripoll: [0047] “At block 360, the result of the analysis is output. According to an embodiment, the output value is a blood pressure reading for a particular patient.” [0103] “the estimation of the variables of interest, such as systolic blood pressure (SBP), diastolic blood pressure (DBP), and mean arterial pressure (MAP), may be determined using a function approximation system 240 of FIG. 2A, in accordance with block 350 of method 300. Such a function approximation system may utilize a regression classification algorithm, such as random forests, a deep belief network trained using restricted Boltzmann machines, a support vector machine, or any other similar regression classification algorithm. Such an algorithm used may have been trained for a specific type of output (e.g., SBP, DBP, and/or MAP) using known clinical parameters, PPG signals, and output values for a training set of patients.” Mulligan: [0047] “G. Displaying an estimate and/or prediction of a patients current and/or future blood pressure status.”).
Regarding claim 4, the combination of Ripoll/Mulligan discloses the method of claim 1, wherein the training of the learning model by setting the sensed photoplethysmography as the input variable and setting the estimated target value of the arterial blood pressure in the current time section and the predicted target value of the arterial blood pressure after the current time section as the output variable includes training the learning model by setting the photoplethysmography and the estimated target value of the arterial blood pressure in the current time section as the input variables of the learning model and setting the predicted target value of the arterial blood pressure after the current time section as the output variable (Ripoll: [0040] “clinical parameters and PPG pulse shapes may be obtained from a patient having an unknown blood pressure. This information may then be pre-processed to obtain a fixed length vector describing the PPG signal and incorporating the clinical parameters of the patient. This fixed length vector may be used by the trained machine learning algorithm to calculate the blood pressure of the patient.” Mulligan: “[0095] At block 235, the method 200 might include updating the model(s) based on a comparison of the patient's directly-measured (or estimated) blood pressure at a given time with the predictions made at past times. Once again, such direct measurements can be fed back into the model(s) to improve their predictive value. After models have been updated, the models can be used for further analysis of measured/derived physiological parameters, as shown by the broken lines on FIG. 2.”),
and the outputting of the estimated target value or the predicted target value of the arterial blood pressure by inputting the photoplethysmography based on the learning model and then performing the deep learning includes outputting the predicted target value of the arterial blood pressure by inputting the photoplethysmography and the estimated target value of the arterial blood pressure based on the learning model and then performing the deep learning (Ripoll: [0103] “in accordance with block 350 of method 300. Such a function approximation system may utilize a regression classification algorithm, such as random forests, a deep belief network trained using restricted Boltzmann machines, a support vector machine, or any other similar regression classification algorithm. Such an algorithm used may have been trained for a specific type of output (e.g., SBP, DBP, and/or MAP) using known clinical parameters, PPG signals, and output values for a training set of patients.” Mulligan: [0047] “G. Displaying an estimate and/or prediction of a patients current and/or future blood pressure status.”).
Regarding claim 6, the combination of Ripoll/Mulligan discloses the method of claim 1, wherein the training of the predetermined learning model that is pre-constructed by setting the sensed photoplethysmography as the input variable and setting the estimated target value of the arterial blood pressure in the current time section and the predicted target value of the arterial blood pressure after the current time section as the output variable includes training the learning model by setting the photoplethysmography and an actual measurement value of the arterial blood pressure in the current time section as the input variable of the learning model and setting the predicted target value of the arterial blood pressure after the current time section as the output variable (Ripoll: [0040] “clinical parameters and PPG pulse shapes may be obtained from a patient having an unknown blood pressure. This information may then be pre-processed to obtain a fixed length vector describing the PPG signal and incorporating the clinical parameters of the patient. This fixed length vector may be used by the trained machine learning algorithm to calculate the blood pressure of the patient.” Mulligan: “[0095] At block 235, the method 200 might include updating the model(s) based on a comparison of the patient's directly-measured (or estimated) blood pressure at a given time with the predictions made at past times. Once again, such direct measurements can be fed back into the model(s) to improve their predictive value. After models have been updated, the models can be used for further analysis of measured/derived physiological parameters, as shown by the broken lines on FIG. 2.” [0093] “the patient's blood pressure can be measured directly (using conventional techniques), and these direct measurements (at block 235) can be fed back into the model to update the model and thereby improve performance of the algorithms in the model (e.g., by refining the weights given to different parameters in terms of estimative or predictive value).”), and the outputting of the estimated target value or the predicted target value of the arterial blood pressure by inputting the photoplethysmography based on the learning model and then performing the deep learning includes outputting the predicted target value of the arterial blood pressure by inputting the photoplethysmography and the measurement value of the arterial blood pressure based on the learning model and then performing the deep learning (Ripoll: [0103] “in accordance with block 350 of method 300. Such a function approximation system may utilize a regression classification algorithm, such as random forests, a deep belief network trained using restricted Boltzmann machines, a support vector machine, or any other similar regression classification algorithm. Such an algorithm used may have been trained for a specific type of output (e.g., SBP, DBP, and/or MAP) using known clinical parameters, PPG signals, and output values for a training set of patients.” Mulligan: [0047] “G. Displaying an estimate and/or prediction of a patients current and/or future blood pressure status.”).
Regarding claim 7, the combination of Ripoll/Mulligan discloses the method of claim 1, further comprising displaying the estimated target value or the predicted target value of the arterial blood pressure (Mulligan: [0047] “G. Displaying an estimate and/or prediction of a patients current and/or future blood pressure status.”).
Regarding claim 8, the combination of Ripoll/Mulligan discloses the method of claim 7, further comprising providing a warning alarm when the estimated target value or the predicted target value of the arterial blood pressure deviates from a preset threshold range (Mulligan: [0098] “any blood pressure trends outside of the normal range would set off various alarm conditions, such as an audible alarm, a message to a physician, a message to the patient, an update written automatically to a patient's chart, etc. Such messaging could be accomplished by electronic mail, text message, etc., and a sensor device or monitoring computer could be configured with, e.g., an SMTP client, text messaging client, or the like to perform such messaging.”).
Regarding claim 11, Ripoll teaches a system for estimating arterial blood pressure based on deep learning ([0025] “FIG. 2A is a diagram of various systems for obtaining blood pressure values”), the system comprising:
a sensing device configured to sense photoplethysmography from a predetermined body part ([0036] “System 210 is a PPG pulse system which may provide an SpO2 level;” [0043] “At block 320, an electronic PPG signal is captured from a measurement location on a patient. The measurement location may be, for example and without limitation, a finger or an ear lobe.”); and
an arterial blood pressure estimation device ([0036] “System 230 may be a pre-processing system to output a fixed length vector in accordance with embodiments. Estimator function system 240 may estimate a patient's blood pressure by analyzing the fixed length vector output by system 230. Further, post-processing system 250 may correct error in the values output by estimator function system 240. Blood pressure system 260 may output the blood pressure of the patient in accordance with embodiments.”) which trains a learning model by setting the photoplethysmography provided from the sensing device as an input variable of a predetermined learning model that is pre-constructed and setting an estimated target value of the arterial blood pressure in a current time section as an output variable ([0103] “the estimation of the variables of interest, such as systolic blood pressure (SBP), diastolic blood pressure (DBP), and mean arterial pressure (MAP), may be determined using a function approximation system 240 of FIG. 2A, in accordance with block 350 of method 300. Such a function approximation system may utilize a regression classification algorithm, such as random forests, a deep belief network trained using restricted Boltzmann machines, a support vector machine, or any other similar regression classification algorithm. Such an algorithm used may have been trained for a specific type of output (e.g., SBP, DBP, and/or MAP) using known clinical parameters, PPG signals, and output values for a training set of patients.”).
However, Ripoll fails to disclose outputting a predicted blood pressure value for after the current time section. Mulligan discloses and a predicted target value of the arterial blood pressure after the current time section as an output variable ([0047] “G. Displaying an estimate and/or prediction of a patients current and/or future blood pressure status.” [0094] “At block 230, the method 200 can include predicting a patient's future blood pressure. Similar to the estimate of the patient's current blood pressure, the prediction of the patient's future blood pressure is based on analysis of the monitored sensor data (either analysis of the monitored data itself, analysis of parameters derived from the monitored data, such as CRI, or both). A number of different predictions can be made by various embodiments, again depending on the types of models generated to analyze the data. For instance, embodiments can predict when a patient's blood pressure will increase or decrease to a specified value. Alternatively and/or additionally, embodiments can predict when a patient's blood pressure will increase or decrease by a specified amount.”).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Ripoll to include a predicted target value of the arterial blood pressure after the current time section as an output variable as disclosed in Mulligan to further help a patient or clinician better monitor blood pressure and a patent's response to treatment or degrading/improving health on an acute or a chronic basis (Mulligan [0092, 0098]).
The combination of Ripoll/Mulligan discloses and which outputs the estimated target value or the predicted target value of the arterial blood pressure by performing deep learning on the photoplethysmography based on the learning model (Ripoll: [0047] “At block 360, the result of the analysis is output. According to an embodiment, the output value is a blood pressure reading for a particular patient.” [0103] “the estimation of the variables of interest, such as systolic blood pressure (SBP), diastolic blood pressure (DBP), and mean arterial pressure (MAP), may be determined using a function approximation system 240 of FIG. 2A, in accordance with block 350 of method 300. Such a function approximation system may utilize a regression classification algorithm, such as random forests, a deep belief network trained using restricted Boltzmann machines, a support vector machine, or any other similar regression classification algorithm. Such an algorithm used may have been trained for a specific type of output (e.g., SBP, DBP, and/or MAP) using known clinical parameters, PPG signals, and output values for a training set of patients.” Mulligan: [0047] “G. Displaying an estimate and/or prediction of a patients current and/or future blood pressure status.”).
Regarding claim 14, the combination of Ripoll/Mulligan discloses the system of claim 11, wherein the arterial blood pressure estimation device trains the learning model by setting the photoplethysmography and the estimated target value or an actual measurement value of the arterial blood pressure in the current time section as the input variable of the learning module in the current time section, and setting the predicted target value of the arterial blood pressure after the current time section as the output variable (Ripoll: [0040] “clinical parameters and PPG pulse shapes may be obtained from a patient having an unknown blood pressure. This information may then be pre-processed to obtain a fixed length vector describing the PPG signal and incorporating the clinical parameters of the patient. This fixed length vector may be used by the trained machine learning algorithm to calculate the blood pressure of the patient.” Mulligan: “[0095] At block 235, the method 200 might include updating the model(s) based on a comparison of the patient's directly-measured (or estimated) blood pressure at a given time with the predictions made at past times. Once again, such direct measurements can be fed back into the model(s) to improve their predictive value. After models have been updated, the models can be used for further analysis of measured/derived physiological parameters, as shown by the broken lines on FIG. 2.”), and the photoplethysmography and a measurement value of the arterial blood pressure or the actual measurement value of the arterial blood pressure are input based on the learning model, and the predicted target value of the arterial blood pressure is output (Ripoll: [0103] “in accordance with block 350 of method 300. Such a function approximation system may utilize a regression classification algorithm, such as random forests, a deep belief network trained using restricted Boltzmann machines, a support vector machine, or any other similar regression classification algorithm. Such an algorithm used may have been trained for a specific type of output (e.g., SBP, DBP, and/or MAP) using known clinical parameters, PPG signals, and output values for a training set of patients.” Mulligan: [0047] “G. Displaying an estimate and/or prediction of a patients current and/or future blood pressure status.”).
Regarding claim 16, the combination of Ripoll/Mulligan discloses the system of claim 11, further comprising a display configured to display the estimated target value or the predicted target value of the arterial blood pressure (Mulligan: [0014] “displaying (e.g., on a display device) an estimate and/or prediction of the blood pressure value of the patient.” [0047] “G. Displaying an estimate and/or prediction of a patients current and/or future blood pressure status.”).
Regarding claim 17, the combination of Ripoll/Mulligan discloses the system of claim 16, further comprising a warning alarm device configured to provide a warning alarm when the estimated target value or the predicted target value of the arterial blood pressure deviates from a preset threshold range (Mulligan: [0098] “any blood pressure trends outside of the normal range would set off various alarm conditions, such as an audible alarm, a message to a physician, a message to the patient, an update written automatically to a patient's chart, etc. Such messaging could be accomplished by electronic mail, text message, etc., and a sensor device or monitoring computer could be configured with, e.g., an SMTP client, text messaging client, or the like to perform such messaging.”).
Claim(s) 2 and 12 is/are rejected under 35 U.S.C. 103 as being unpatentable over Ripoll (US 20130012823 A1) in view of Mulligan (US 20150065826 A1), and in further view of Otsuki (US 20230072934 A1).
Regarding claim 2, the combination of Ripoll/Mulligan discloses the method of claim 1. However, the combination of Ripoll/Mulligan fails to disclose training using generated or measured noise.
Otsuki teaches a system and methods for restoration of a signal representing living body information such as heartbeat behavior is restored by using artificial intelligence (AI) from data obtained by measuring a subject. Otsuki discloses wherein the learning model is pre-trained by including virtually generated noise or actually generated and measured noise ([0210] “At step S307, the signal restoration system 1 estimates the blood pressure.” [0199] “the second learning data may be generated by adding a noise component of an illustrated Gaussian distribution to the aortic pulse wave signal PWS in the ideal state”).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the combination of Ripoll/Mulligan to include training using generated noise as disclosed in Otsuki because when the learning model is subjected to learning in accordance with a noise distribution, noise can be accurately attenuated to extract the aortic pulse wave signal PWS (Otsuki [0202]).
Regarding claim 12, the combination of Ripoll/Mulligan discloses the system of claim 11. However, the combination of Ripoll/Mulligan fails to disclose training using generated or measured noise.
Otsuki discloses wherein the arterial blood pressure estimation device trains the learning model by including virtually generated noise or actually generated and measured noise in training data ([0210] “At step S307, the signal restoration system 1 estimates the blood pressure.” [0199] “the second learning data may be generated by adding a noise component of an illustrated Gaussian distribution to the aortic pulse wave signal PWS in the ideal state”).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the combination of Ripoll/Mulligan to include training using generated noise as disclosed in Otsuki because when the learning model is subjected to learning in accordance with a noise distribution, noise can be accurately attenuated to extract the aortic pulse wave signal PWS (Otsuki [0202]).
Claim(s) 3, 5, 13, and 15 is/are rejected under 35 U.S.C. 103 as being unpatentable over Ripoll (US 20130012823 A1) in view of Mulligan (US 20150065826 A1), and in further view of Chenagi (US 20210353164 A1).
Regarding claim 3, the combination of Ripoll/Mulligan discloses the method of claim 1, wherein the outputting of the estimated target value or the predicted target value of the arterial blood pressure by inputting the photoplethysmography based on the learning model and then performing the deep learning includes calculating estimated target values or predicted target values of a diastolic blood pressure value and a systolic blood pressure value of the arterial blood pressure (Ripoll: [0103] “the estimation of the variables of interest, such as systolic blood pressure (SBP), diastolic blood pressure (DBP), and mean arterial pressure (MAP), may be determined using a function approximation system 240 of FIG. 2A, in accordance with block 350 of method 300. Such a function approximation system may utilize a regression classification algorithm, such as random forests, a deep belief network trained using restricted Boltzmann machines, a support vector machine, or any other similar regression classification algorithm. Mulligan: [0047] “G. Displaying an estimate and/or prediction of a patients current and/or future blood pressure status.”).
However, the combination of Ripoll/Mulligan fails to disclose explicitly using the maximum and minimum estimated or predicted blood pressure values to determine the diastolic and systolic blood pressure values. Chegani teaches a method and wearable device for measuring blood pressure. Chenagi discloses calculating a diastolic blood pressure value and a systolic blood pressure value from a maximum value and a minimum value of the estimated target value of the arterial blood pressure or the predicted target value of the arterial blood pressure ([0110] “blood pressure encompasses any measure relating to blood pressure such as a systolic and/or mean and/or diastolic measure. Blood pressure is related to the full shape of pulse pressure. In some cases, a maximum point (the systolic blood pressure) of a pulse cycle and/or the minimum (the diastolic blood pressure) of a pulse cycle can be determined.”).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the combination of Ripoll/Mulligan to include using the maximum and minimum estimated or predicted blood pressure values to determine the diastolic and systolic blood pressure values as disclosed in Chegani to extract systolic and diastolic blood pressure from pulse cycled data obtained by PPG (Chegani [0108, 0110]).
Regarding claim 5, the combination of Ripoll/Mulligan discloses the method of claim 4, wherein the outputting of the estimated target value or the predicted target value of the arterial blood pressure by inputting the photoplethysmography based on the learning model and then performing the deep learning includes calculating predicted target values of a diastolic blood pressure value and a systolic blood pressure value of the arterial blood pressure (Ripoll: [0103] “the estimation of the variables of interest, such as systolic blood pressure (SBP), diastolic blood pressure (DBP), and mean arterial pressure (MAP), may be determined using a function approximation system 240 of FIG. 2A, in accordance with block 350 of method 300. Such a function approximation system may utilize a regression classification algorithm, such as random forests, a deep belief network trained using restricted Boltzmann machines, a support vector machine, or any other similar regression classification algorithm. Mulligan: [0047] “G. Displaying an estimate and/or prediction of a patients current and/or future blood pressure status.” [0094] “At block 230, the method 200 can include predicting a patient's future blood pressure. Similar to the estimate of the patient's current blood pressure, the prediction of the patient's future blood pressure is based on analysis of the monitored sensor data”).
However, the combination of Ripoll/Mulligan fails to disclose explicitly using the maximum and minimum predicted blood pressure values to determine the diastolic and systolic blood pressure values. Chenagi discloses calculating a diastolic blood pressure value and a systolic blood pressure value from a maximum value and a minimum value of the predicted target value of the arterial blood pressure ([0110] “blood pressure encompasses any measure relating to blood pressure such as a systolic and/or mean and/or diastolic measure. Blood pressure is related to the full shape of pulse pressure. In some cases, a maximum point (the systolic blood pressure) of a pulse cycle and/or the minimum (the diastolic blood pressure) of a pulse cycle can be determined.”).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the combination of Ripoll/Mulligan to include using the maximum and minimum predicted blood pressure values to determine the diastolic and systolic blood pressure values as disclosed in Chegani to extract systolic and diastolic blood pressure from pulse cycled data obtained by PPG (Chegani [0108, 0110]).
Regarding claim 13, the combination of Ripoll/Mulligan discloses the system of claim 11, wherein the arterial blood pressure estimation device calculates an estimated target value or a predicted target value of a diastolic blood pressure value and a systolic blood pressure value of the arterial blood pressure (Ripoll: [0103] “the estimation of the variables of interest, such as systolic blood pressure (SBP), diastolic blood pressure (DBP), and mean arterial pressure (MAP), may be determined using a function approximation system 240 of FIG. 2A, in accordance with block 350 of method 300. Such a function approximation system may utilize a regression classification algorithm, such as random forests, a deep belief network trained using restricted Boltzmann machines, a support vector machine, or any other similar regression classification algorithm. Mulligan: [0047] “G. Displaying an estimate and/or prediction of a patients current and/or future blood pressure status.”).
However, the combination of Ripoll/Mulligan fails to disclose explicitly using the maximum and minimum estimated or predicted blood pressure values to determine the diastolic and systolic blood pressure values. Chenagi discloses calculating a diastolic blood pressure value and a systolic blood pressure value from a maximum value and a minimum value of the estimated target value of the arterial blood pressure or the predicted target value of the arterial blood pressure ([0110] “blood pressure encompasses any measure relating to blood pressure such as a systolic and/or mean and/or diastolic measure. Blood pressure is related to the full shape of pulse pressure. In some cases, a maximum point (the systolic blood pressure) of a pulse cycle and/or the minimum (the diastolic blood pressure) of a pulse cycle can be determined.”).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the combination of Ripoll/Mulligan to include using the maximum and minimum estimated or predicted blood pressure values to determine the diastolic and systolic blood pressure values as disclosed in Chegani to extract systolic and diastolic blood pressure from pulse cycled data obtained by PPG (Chegani [0108, 0110]).
Regarding claim 15, the combination of Ripoll/Mulligan discloses the system of claim 14, wherein the arterial blood pressure estimation device calculates predicted target values of a diastolic blood pressure value and a systolic blood pressure value of the arterial blood pressure (Ripoll: [0103] “the estimation of the variables of interest, such as systolic blood pressure (SBP), diastolic blood pressure (DBP), and mean arterial pressure (MAP), may be determined using a function approximation system 240 of FIG. 2A, in accordance with block 350 of method 300. Such a function approximation system may utilize a regression classification algorithm, such as random forests, a deep belief network trained using restricted Boltzmann machines, a support vector machine, or any other similar regression classification algorithm. Mulligan: [0047] “G. Displaying an estimate and/or prediction of a patients current and/or future blood pressure status.” [0094] “At block 230, the method 200 can include predicting a patient's future blood pressure. Similar to the estimate of the patient's current blood pressure, the prediction of the patient's future blood pressure is based on analysis of the monitored sensor data”).
However, the combination of Ripoll/Mulligan fails to disclose explicitly using the maximum and minimum predicted blood pressure values to determine the diastolic and systolic blood pressure values. Chenagi discloses calculating a diastolic blood pressure value and a systolic blood pressure value from a maximum value and a minimum value of the predicted target value of the arterial blood pressure ([0110] “blood pressure encompasses any measure relating to blood pressure such as a systolic and/or mean and/or diastolic measure. Blood pressure is related to the full shape of pulse pressure. In some cases, a maximum point (the systolic blood pressure) of a pulse cycle and/or the minimum (the diastolic blood pressure) of a pulse cycle can be determined.”).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the combination of Ripoll/Mulligan to include using the maximum and minimum predicted blood pressure values to determine the diastolic and systolic blood pressure values as disclosed in Chegani to extract systolic and diastolic blood pressure from pulse cycled data obtained by PPG (Chegani [0108, 0110]).
Claim(s) 9-10 and 18-19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Ripoll (US 20130012823 A1) in view of Mulligan (US 20150065826 A1), and in further view of Maeta (US 20190228860 A1).
Regarding claim 9, the combination of Ripoll/Mulligan discloses the method of claim 1. However, the combination of Ripoll/Mulligan fails to disclose an error signal comparing the estimated target value and the predicted target value of the arterial blood pressure to predict abnormal blood pressure.
Maeta teaches a software, a health condition determination apparatus, and a health condition determination method, each of which can understand different intra-subject variation for each subject with high accuracy by reflecting a vital sign such as blood pressure considering an individual difference of the subject or daily condition of the subject. Maeta discloses further comprising: calculating an error signal of the estimated target value and the predicted target value of the arterial blood pressure; comparing the calculated error signal with a preset threshold value; and predicting an abnormal symptom of the arterial blood pressure based on the comparison result ([0085] “The determination unit determines whether or not the vital information is an abnormal value, by comparing, with a predetermined numerical value, a difference between the mean value μ and a value of a vital sign of the input predetermined vital information or a difference between the mean value μ and the mean μ at the time of measurement on the previous day, and thus can determine whether or not the vital information is an abnormal value, by using the mean value of the vital information reflecting the condition of the same subject before and after the predetermined measurement start time point and the comfortable condition of the same subject. The “predetermined numerical value” stated herein includes, when a value serving as a standard, such as the upper limit, is set, an aspect in which a numerical value serving as an object of determination is determined to be abnormal if equal to or higher than the upper limit, and an aspect in which the numerical value is determined to be abnormal if higher than the upper limit.” [0147] “The vital information 8 contains body temperature, pulse rate, systolic blood pressure, diastolic blood pressure, and respiration rate.”).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the combination of Ripoll/Mulligan to include an error signal comparing the estimated target value and the predicted target value of the arterial blood pressure to predict abnormal blood pressure as disclosed in Maeta to improve the accuracy of determination of health conditions and increase the convenience as a diagnostic support tool (Maeta [0289]).
Regarding claim 10, the combination of Ripoll/Mulligan discloses the method of claim 1. However, the combination of Ripoll/Mulligan fails to disclose an error signal comparing the diastolic and systolic values for the estimated target value and the predicted target value of the arterial blood pressure to predict abnormal blood pressure.
Maeta discloses, further comprising: calculating error values of diastolic and systolic blood pressure values for the estimated target value and the predicted target value of the arterial blood pressure; comparing at least one of diastolic and systolic blood pressure values for the estimated target value and predicted target value of the arterial blood pressure, or the calculated error value with preset threshold values; and predicting an abnormal symptom of the arterial blood pressure based on the comparison result ([0085] “The determination unit determines whether or not the vital information is an abnormal value, by comparing, with a predetermined numerical value, a difference between the mean value μ and a value of a vital sign of the input predetermined vital information or a difference between the mean value μ and the mean μ at the time of measurement on the previous day, and thus can determine whether or not the vital information is an abnormal value, by using the mean value of the vital information reflecting the condition of the same subject before and after the predetermined measurement start time point and the comfortable condition of the same subject. The “predetermined numerical value” stated herein includes, when a value serving as a standard, such as the upper limit, is set, an aspect in which a numerical value serving as an object of determination is determined to be abnormal if equal to or higher than the upper limit, and an aspect in which the numerical value is determined to be abnormal if higher than the upper limit.” [0147] “The vital information 8 contains body temperature, pulse rate, systolic blood pressure, diastolic blood pressure, and respiration rate.”).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the combination of Ripoll/Mulligan to include an error signal comparing the estimated target value and the predicted target value of the arterial blood pressure to predict abnormal blood pressure as disclosed in Maeta to improve the accuracy of determination of health conditions and increase the convenience as a diagnostic support tool (Maeta [0289]).
Regarding claim 18, the combination of Ripoll/Mulligan discloses the system of claim 11. However, the combination of Ripoll/Mulligan fails to disclose an error signal comparing the estimated target value and the predicted target value of the arterial blood pressure to predict abnormal blood pressure.
Maeta discloses wherein the arterial blood pressure estimating device calculates an error signal of the estimated target value and the predicted target value of the arterial blood pressure, compares the calculated error signal with a preset threshold value, and predicts an abnormal symptom of the arterial blood pressure based on the comparison result ([0085] “The determination unit determines whether or not the vital information is an abnormal value, by comparing, with a predetermined numerical value, a difference between the mean value μ and a value of a vital sign of the input predetermined vital information or a difference between the mean value μ and the mean μ at the time of measurement on the previous day, and thus can determine whether or not the vital information is an abnormal value, by using the mean value of the vital information reflecting the condition of the same subject before and after the predetermined measurement start time point and the comfortable condition of the same subject. The “predetermined numerical value” stated herein includes, when a value serving as a standard, such as the upper limit, is set, an aspect in which a numerical value serving as an object of determination is determined to be abnormal if equal to or higher than the upper limit, and an aspect in which the numerical value is determined to be abnormal if higher than the upper limit.” [0147] “The vital information 8 contains body temperature, pulse rate, systolic blood pressure, diastolic blood pressure, and respiration rate.”).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the combination of Ripoll/Mulligan to include an error signal comparing the estimated target value and the predicted target value of the arterial blood pressure to predict abnormal blood pressure as disclosed in Maeta to improve the accuracy of determination of health conditions and increase the convenience as a diagnostic support tool (Maeta [0289]).
Regarding claim 19, the combination of Ripoll/Mulligan discloses the system of claim 11. However, the combination of Ripoll/Mulligan fails to disclose an error signal comparing the diastolic and systolic values for the estimated target value and the predicted target value of the arterial blood pressure to predict abnormal blood pressure.
Maeta discloses, wherein the arterial blood pressure estimating device calculates an error value of diastolic and systolic blood pressure values for the estimated target value and the predicted target value of the arterial blood pressure, compares at least one of the diastolic and systolic blood pressure values for the estimated target value and the predicted target value of the arterial blood pressure or the calculated error value with preset threshold values, and predicts the abnormal symptom of the arterial blood pressure based on the comparison result ([0085] “The determination unit determines whether or not the vital information is an abnormal value, by comparing, with a predetermined numerical value, a difference between the mean value μ and a value of a vital sign of the input predetermined vital information or a difference between the mean value μ and the mean μ at the time of measurement on the previous day, and thus can determine whether or not the vital information is an abnormal value, by using the mean value of the vital information reflecting the condition of the same subject before and after the predetermined measurement start time point and the comfortable condition of the same subject. The “predetermined numerical value” stated herein includes, when a value serving as a standard, such as the upper limit, is set, an aspect in which a numerical value serving as an object of determination is determined to be abnormal if equal to or higher than the upper limit, and an aspect in which the numerical value is determined to be abnormal if higher than the upper limit.” [0147] “The vital information 8 contains body temperature, pulse rate, systolic blood pressure, diastolic blood pressure, and respiration rate.”).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the combination of Ripoll/Mulligan to include an error signal comparing the estimated target value and the predicted target value of the arterial blood pressure to predict abnormal blood pressure as disclosed in Maeta to improve the accuracy of determination of health conditions and increase the convenience as a diagnostic support tool (Maeta [0289]).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MOLLY HALPRIN whose telephone number is (703)756-1520. The examiner can normally be reached 12PM-8PM ET.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Robert (Tse) Chen can be reached at (571) 272-3672. 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.
/M.H./Examiner, Art Unit 3791
/DEVIN B HENSON/Primary Examiner, Art Unit 3791
Prosecution Insights