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 .
Election/Restrictions
Applicant's election with traverse of claims 1-6 in the reply filed on 09/09/2025 is acknowledged. The traversal is on the ground(s) that amendments to claim 16 make them no longer in condition for restriction. This is found persuasive. As such, the restriction, filed 07/10/2025, with regards to Invention I (claims 1-6) and Invention III (claims 16-20) is withdrawn. Claims 1-6 and 16-20 are hereby being fully examined for patentability.
Claims 7-15 are cancelled.
Claims 1-6 and 16-21 are hereby under examination.
Information Disclosure Statement
The information disclosure statements (IDS) submitted on 03/31/2023, 06/21/2023, and 09/27/2024 are in compliance with the provision of 37 CFR 1.97. Accordingly, the IDS are being considered.
Drawings
The drawings are objected to because paragraph [0112] of the specification states model absorbances and average measured absorbances are superimposed and shown in two different colors in fig 4. However, the drawings are in black and white, and as such, the model absorbances and average measured absorbances cannot be differentiated in the figure. 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.
Specification
The use of the terms “Wi-Fi”, “Bluetooth”, and “ZigBee”, which are trade names or marks used in commerce, has been noted in this application. The terms should be accompanied by the generic terminology; furthermore the terms should be capitalized wherever it appears or, where appropriate, include a proper symbol indicating use in commerce such as ™, SM , or ® following the term.
Although the use of trade names and marks used in commerce (i.e., trademarks, service marks, certification marks, and collective marks) are permissible in patent applications, the proprietary nature of the marks should be respected and every effort made to prevent their use in any manner which might adversely affect their validity as commercial marks.
Claim Objections
Claims 1, 5, 16, and 20 are objected to because of the following informalities: "the model" should read "the electric-analog model" for claim language consistency. Appropriate correction is required.
Claims 4, 5, 18, and 19 are objected to because of the following informalities: "the network" should read "the machine learning network" for claim language consistency. Appropriate correction is required.
Claim 16 is objected to because of the following informalities: “transforming the model output” should read “transform the model output” and “training a machine-learned network” should read “train a machine-learned network”. 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 1-6 and 16-21 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.
Regarding Claims 1 and 16, the claims recite “fitting the parameters of the model”. There is insufficient antecedent basis for “the parameters”. For the purposes of examination, “fitting the parameters” is herein interpreted as “fitting parameters”. The claims also recite “the training comprises: acquiring measured hearing loss data; fitting the parameters of the model such that the transformed model output correlates to the measured hearing data; and identifying one or more classifiers of the transformed model output that provides an estimate of the hearing loss”. According to the spec, the “one or more classifiers” are the “regression multipliers” shown in Figures 13 and 15 (“Again, a logistic regression analysis (e.g., a machine learning network) can be used to identify MECL regression multipliers that correlate the middle-ear model feature extraction data, which includes the fitted parameters of the analog model, with the assessed/measured data from patients to identify regression multipliers, also known as classifiers.” from paragraph [0134] of the specification). What does it mean for the transformed model output (which is a value) to have a regression multiplier? And when read together, that last limitation reads as “identifying a multiplier of a value that provides an estimate for the hearing loss”. It is unclear how a multiplier of a value provides an estimate for the hearing loss. Due to the aforementioned reasons, claims 1 and 16 are rendered indefinite. Claims 2-6 and 17-21 are rejected due to their dependence on claims 1 and 16, respectively.
Regarding Claims 4 and 18, the claims recite “a transmission line representing the ear canal terminated by the network”. It is unclear what is meant by this limitation. Is the ear canal terminated by the network or the transmission line? Additionally, it is unclear how the machine learning/machine-learned network, recited in claims 1 and 16, performs the recited termination. Therefore, claims 4 and 18 are rendered indefinite. Claims 5 and 19 are further rejected due to their dependence on claims 4 and 18, respectively.
Regarding Claims 5 and 19, the claims recite “the network of the model comprises three parallel branches”. There is insufficient antecedent basis for “the network of the model”. It is unclear how the electric-analog model can have the machine learning/machine-learned network, recited in claims 1 and 16. Furthermore, it is unclear how the machine learning/machine-learned network can comprise three parallel branches, with each branch comprising a stiffness, damping, and mass component if the parallel branches are physical circuit components. It is also unclear how the machine learning/machine-learned network represents mechanics of a tympanic membrane coupled to ossicles of an ear. Therefore, claims 5 and 19 are rendered indefinite. Claim 20 is further rejected due to its dependence on claim 19.
Further regarding Claim 16, the claim recites “obtain model outputs; transforming the model output”. There is lack of proper antecedent basis for “the model output”. It is unclear which of the plural model outputs is being transformed. For the purposes of examination, “transforming the model output” is herein interpreted to be “transforming one of the model outputs”. Due to the aforementioned reason, claim 16 is further rendered indefinite. Claims 17-21 are further rejected due to their dependence on claim 16.
Regarding Claim 17, the claim recites “the classifiers”. Claim 16, from which claim 17 is dependent, recites “one or more classifiers”. When claim 16 is interpreted to be one classifier, there is lack of proper antecedent basis for “the classifiers”. For the purposes of examination, “the classifiers” are herein interpreted to be “the one or more classifiers”. The claim also recites “the ossicular loss level outputs” and “the pure tone average”. There is insufficient antecedent basis for these claim limitations. For the purposes of examination, “the ossicular loss level outputs” is herein interpreted to be ossicular loss level outputs and “the pure tone average” is herein interpreted to be a pure tone average. Due to the aforementioned reasons, claim 17 is rendered indefinite.
Regarding Claim 20, the claim recites “the transmission line of the model represent an ear canal”. It is unclear if “an ear canal” is the same as or different than “the ear canal” recited in claim 18, from which claim 20 is dependent. For the purposes of examination, “an ear canal” is herein interpreted to be the same as or different than “the ear canal” recited in claim 18. Due to the aforementioned reason, claim 20 is rendered indefinite.
Regarding Claim 21, the claim recites a series of steps including identifying a classifier and transforming the model outputs. However, claim 16, from which claim 21 is dependent, is an apparatus claim. It is unclear how claim 21 further limits claim 16 or what structural component is configured to perform the recited steps. For the purposes of examination, it is herein interpreted that “the device including a computer readable medium” is further configured to perform the steps recited in claim 21. The claim also recites “identify a classifier indicating an ear type”. It is unclear if “a classifier” is the same as or different than the “one of more classifiers” recited in claim 16, from which claim 21 is dependent. For the purposes of examination, “a classifier” is herein interpreted to be the same as or different than the “one of more classifiers” recited in claim 16. Furthermore, the claim recites “based on the identified ear type, transform the model outputs to estimate the hearing loss”. It is unclear how the hearing loss is estimated. In claim 16, hearing loss is estimated by “identifying one or more classifiers of the transformed model output”. Therefore, it is unclear how hearing loss is estimated in claim 21 by transforming the model outputs based on a classifier if classifiers are based on model outputs. Due to the aforementioned reason, claim 21 is rendered indefinite. Claims 17-20 are further rejected due to their dependence on claim 21.
In light of the rejections of claims 17-21 for indefiniteness under 35 U.S.C. 112 2nd paragraph, as set forth above, the Examiner was not able to perform a meaningful search of the prior art. Applicant is reminded that prior art rejections under 35 U.S.C. 102 and/or 35 U.S.C. 103 may be applied in the next Office action in light of applicant's amendments, and that the next Office action can properly be made "Final" if these rejections are necessitated by amendment. See MPEP 706.07.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-6 and 16-21 are rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter. The claim(s) as a whole, considering all claim elements both individually and in combination, do not amount to significantly more than an abstract idea. A streamlined analysis of claim 1 follows.
STEP 1
Regarding claim 1, the claim recites a series of steps or acts, including obtaining an acoustic measurement from an ear canal. Thus, the claim is directed to a process, which is one of the statutory categories of invention.
STEP 2A, PRONG ONE
The claim is then analyzed to determine whether it is directed to any judicial exception. The steps of set transforming the model output to a measured absorbance to determine an averaged absorbance over a frequency range converted to decibels; and training a machine learning network, wherein the training comprises: acquiring measured hearing loss data; fitting the parameters of the model such that the transformed model output correlates to the measured hearing data; and identifying one or more classifiers of the transformed model output that provides an estimate of the hearing loss set forth a judicial exception. These steps describes a concept performed in the human mind or by a human using a pen and paper (including an observation, evaluation, judgment, opinion). Thus, the claim is drawn to a Mental Process, which is an Abstract Idea.
STEP 2A, PRONG TWO
Next, the claim as a whole is analyzed to determine whether the claim recites additional elements that integrate the judicial exception into a practical application. The claim fails to recite an additional element or a combination of additional elements to apply, rely on, or use the judicial exception in a manner that imposes a meaningful limitation on the judicial exception. Claim 1 fails to recite any additional elements that integrate the judicial exception into a practical application. The Abstract Idea alone does not provide an improvement to the technological field, the method does not effect a particular treatment or effect a particular change based on the Abstract Idea, nor does the method use a particular machine to perform the Abstract Idea.
STEP 2B
Next, the claim as a whole is analyzed to determine whether any element, or combination of elements, is sufficient to ensure that the claim amounts to significantly more than the exception. Besides the Abstract Idea, the claim recites additional steps of obtaining an acoustic measurement from an ear canal; modeling the acoustic measurement with an electric-analog model to obtain a model output. Obtaining data (acoustic measurement data) in order to determine hearing loss is well-understood, routine and conventional activity for those in the field of medical diagnostics. Further, the obtaining step is recited at a high level of generality such that it amounts to insignificant presolution activity, e.g., mere data gathering step necessary to perform the Abstract Idea. When recited at this high level of generality, there is no meaningful limitation, such as a particular or unconventional step that distinguishes it from well-understood, routine, and conventional data gathering and comparing activity engaged in by medical professionals prior to Applicant's invention. Furthermore, it is well established that the mere physical or tangible nature of additional elements such as the obtaining step does not automatically confer eligibility on a claim directed to an abstract idea (see, e.g., Alice Corp. v. CLS Bank Int'l, 134 S.Ct. 2347, 2358-59 (2014)).
Consideration of the additional elements as a combination also adds no other meaningful limitations to the exception not already present when the elements are considered separately. Unlike the eligible claim in Diehr in which the elements limiting the exception are individually conventional, but taken together act in concert to improve a technical field, the claim here does not provide an improvement to the technical field. Even when viewed as a combination, the additional elements fail to transform the exception into a patent-eligible application of that exception. Thus, the claim as a whole does not amount to significantly more than the exception itself. The claim is therefore drawn to non-statutory subject matter.
Regarding claim 16, the device recited in the claim is a generic device comprising generic components configured to perform the abstract idea. The recited device is a generic device configured to perform pre-solutional data gathering activity, and the recited device’s computer readable medium is configured to perform the Abstract Idea. According to section 2106.05(f) of the MPEP, merely using a computer as a tool to perform an abstract idea does not integrate the Abstract Idea into a practical application.
The dependent claims also fail to add something more to the abstract independent claims as they further limit limitations recited in the independent claims and generally recite method steps pertaining to data modeling. The modeling step recited in the independent claims maintains a high level of generality even when considered in combination with the dependent claims. Further defining the “acoustic measurement”, the “electric-analog model”, and the “classifiers” fails to further define the Abstract or add any meaningful limitations to the independent claims.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claim(s) 1-5 is/are rejected under 35 U.S.C. 103 as being unpatentable over Prieve et al. (Prediction of Conductive Hearing Loss Using Wideband Acoustic Immittance – cited by Applicant) hereinafter Prieve, in view of Withnell & Gowdy (An Analysis of the Acoustic Input Impedance of the Ear) hereinafter Withnell, and further in view of Grais et al. (Analysing wideband absorbance immittance in normal and ears with otitis media with effusion using machine learning – cited by Applicant) hereinafter Grais.
Regarding Claim 1, Prieve discloses a method of estimating hearing loss (the effectiveness of wideband acoustic immittance (WAI) and tympanometry in detecting conductive hearing loss (CHL) (abstract)), comprising:
obtaining an acoustic measurement from an ear canal (Three studies collected WAI in groups of adults with CHL whose etiologies were surgically confirmed. (Wideband Middle Ear Measures in Adults, para. 1));
transforming an output of the acoustic measurement to a measured absorbance to determine an averaged absorbance over a frequency range converted to decibels (Some studies reported wideband absorbance (A), which is the power absorbed by the outer/middle ear under ambient conditions and is computed as 1− |R|^2. Although Keefe and Simmons (2003) reported on the measure “transmittance,” the equation used was the same as that for A. Rosowski et al. (2012) and Nakajima et al. (2012) computed A and transformed their data to a dB scale by using the equation 10 × Log (A), and is denoted as AdB in this article. (Introduction, para. 3); The mean |R|2 and AdB for these participant groups are illustrated in Figure 4A, B, respectively.(Wideband Middle Ear Measures in Adults, para. 1); An alternative method for measuring the properties of the outer ear/middle ear system has emerged in which broadband stimuli are presented and responses measured using a carefully, acoustically described probe that allows calculation of acoustic admittance as well as a host of other physical measures, such as acoustic impedance, power reflectance (R2), and power absorbance. (Introduction, para. 2)).
Prieve fails to disclose modeling the acoustic measurement with an electric-analog model to obtain a model output;
and training a machine learning network, wherein the training comprises:
acquiring measured hearing loss data;
fitting the parameters of the model such that the transformed model output correlates to the measured hearing data; and
identifying one or more classifiers of the transformed model output that provides an estimate of the hearing loss.
However, Withnell teaches modeling an acoustic measurement (Sound pressure measurements were made in one ear of subjects aged 18–30 years, the location of measurement being near the isthmus. (Methods, Subject and Data Collection, para. 1)) with an electric-analog model to obtain a model output (The ear was modeled as a one-dimensional lossy transmission line terminated by a distributed load impedance (a non-rigid termination), applicable to plane wave sound propagation. The ear canal was represented by a lossy transmission line. (Methods, Modeling and Data Analysis, para. 1); This type of model captures well the acoustic input impedance of the middle ear. (Methods, under equation 29); Sound pressure measurements in the ear canal using an acoustically calibrated sound source provide for the derivation of the acoustic input impedance of the ear, providing a window into the acoustico-mechanical function of the ear. This study investigated the respective contributions of the ear canal, the middle ear, and the cochlea to the acoustic input impedance of the ear by modeling the ear as a one-dimensional lossy transmission line terminated by a distributed load impedance. (Discussion, para. 1); fig 1).
Withnell is considered analogous art to the present invention because it is directed towards the same field of endeavor.
It would have been obvious to one having ordinary skill in the art at the time of the effective filing date to have modified the method of Prieve such that it includes the step of modeling the acoustic measurement with an electric-analog model to obtain a model output, as taught by Withnell, because it would allow for the derivation of the acoustic input impedance of the ear canal and impedance of the ear canal is related to middle-ear pathologies as evidenced by Voss et al. (Acoustic Mechanisms that Determine the Ear-Canal Sound Pressures Generated by Earphones). See Introduction, B., paragraph 1.
The modified method of Prieve in view of Withnell teaches transforming the model output to a measured absorbance to determine an averaged absorbance over a frequency range converted to decibels.
Prieve in view of Withnell fails to teach training a machine learning network, wherein the training comprises:
acquiring measured hearing loss data;
fitting the parameters of the model such that the transformed model output correlates to the measured hearing data; and
identifying one or more classifiers of the transformed model output that provides an estimate of the hearing loss.
However, Grais teaches a method of estimating hearing loss (This study aimed to develop Machine Learning (ML) tools to identify the WAI absorbance characteristics across different frequency-pressure regions in the normal middle ear and ears with otitis media with effusion (OME) to enable diagnosis of middle ear conditions automatically. (Abstract)) comprising: training a machine learning network (Development of machine learning (ML) models for WAI classification (Materials and Methods, Methods, Development of machine learning (ML) models for WAI classification)), wherein the training comprises:
acquiring measured hearing loss data (A total of 672 WAI data were collected from patients and volunteers in five hospitals in Beijing, Guangzhou and Xuzhou, China. There were 423 ears from 242 participants with normal middle ear function (age range 1–68), and 249 ears with OME from 163 participants (age range 1–73 years). (Materials and Methods, Materials, Wideband absorbance immittance (WAI) data acquisition); Figure 1c shows a 2D image using the domains of frequency and pressure corresponding to the WAI data in Fig. 1a. (Materials and Methods, Methods, WAI measuring system and data pre-processing); Basic ML classifiers were used to process the 2D WAI images after interpolating the pressure axis (Materials and Methods, Methods, Development of machine learning (ML) models for WAI classification));
fitting parameters of a model such that a model output correlates to the measured hearing data (As indicated in section “Methods”, different ML classifiers were developed and examined to determine their ability to categorise middle ear function as normal or OME using the 2D frequency-pressure WAI images... To train the FNN and CNN models, the binary cross entropy cost function and Adam optimizer were used. Because the initialization of the FNNs and CNNs is important, each model was trained three times with different random initialization for each training, i.e., training three models with the same structure but with different initializations. (Results, Outputs from various classification models: accuracy, area under the ROC curve, F1 score, precision and recall for categorising middle ear function as normal or OME)); and
identifying one or more classifiers of the model output that provides an estimate of the hearing loss (Further statistical analysis at each frequency-pressure point showed 88% of data points (4782 out of 5457) to have significant differences in absorbance values between normal ears and OME ears (Wilcoxon rank sum test, Z = 3.04, p < 0.0005). (Results, WAI characteristics and statistical analysis of the normal middle ear condition compared to ears with OME); the results from the ML classifiers in this study exceed diagnostic performance in identifying normal and OME ear conditions in the primary care settings by General Practitioners (GP) or other healthcare professionals using traditional middle ear diagnostic tools (Discussion and future study, para. 2)).
Grais is considered analogous art to the present invention because it is directed towards the same field of endeavor.
It would have been obvious to one having ordinary skill in the art at the time of the effective filing date to have modified the method of Prieve in view of Withnell such that it includes training a machine learning network, wherein the training comprises: acquiring measured hearing loss data; fitting parameters of a model such that a model output correlates to the measured hearing data; and identifying one or more classifiers of the model output that provides an estimate of the hearing loss, as taught by Grais, because training a machine learning network with known data associated with a disease to predict/estimate the degree or presence of the disease is well-understood, routine, and conventional activity in the art. Furthermore, all the claimed elements were known in the prior art and one skilled in the art could have combined the elements as claimed by known methods with no change in their respective functions, and the combination would have yielded nothing more than predictable results to one of ordinary skill in the art. See KSR International Co. v. Teleflex Inc., 550 U.S. 398, 415-421, 82 USPQ2d 1385, 1395 (2007) (see MPEP §§ 2143, A. and 2143.02).
The modified method of Prieve in view of Withnell and further in view of Grais teaches the training comprises: acquiring measured hearing loss data; fitting parameters of the model such that the transformed model output correlates to the measured hearing data; and identifying one or more classifiers of the transformed model output that provides an estimate of the hearing loss.
Regarding Claim 2, Prieve in view of Withnell and further in view of Grais teaches the invention as discussed above in claim 1. Prieve further discloses the acoustic measurement comprises an impedance-based measurement (An alternative method for measuring the properties of the outer ear/middle ear system has emerged in which broadband stimuli are presented and responses measured using a carefully, acoustically described probe that allows calculation of acoustic admittance as well as a host of other physical measures, such as acoustic impedance, power reflectance (R2), and power absorbance. The term wideband acoustic immittance (WAI) is the umbrella term that includes the various acoustical measures of the outer/middle ear system. (Introduction, para. 2)).
Regarding Claim 3, Prieve in view of Withnell and further in view of Grais teaches the invention as discussed above in claim 2. Prieve discloses the impedance based measurement comprises a wideband acoustic immittance (An alternative method for measuring the properties of the outer ear/middle ear system has emerged in which broadband stimuli are presented and responses measured using a carefully, acoustically described probe that allows calculation of acoustic admittance as well as a host of other physical measures, such as acoustic impedance, power reflectance (R2), and power absorbance. The term wideband acoustic immittance (WAI) is the umbrella term that includes the various acoustical measures of the outer/middle ear system. (Introduction, para. 2)).
Regarding Claim 4, Prieve in view of Withnell and further in view of Grais teaches the invention as discussed above in claim 1. Prieve in view of Withnell and further in view of Grais teaches the step of modeling the acoustic measurement further comprises a transmission line representing the ear canal terminated by the network (The ear was modeled as a one-dimensional lossy transmission line terminated by a distributed load impedance (a non-rigid termination), applicable to plane wave sound propagation. (Methods, Modeling and Data Analysis, para. 1, Withnell)).
Regarding Claim 5, Prieve in view of Withnell and further in view of Grais teaches the invention as discussed above in claim 4. Prieve in view of Withnell and further in view of Grais teaches the network of the model comprises three parallel branches (the eardrum and ossicles using a bank of five simple harmonic oscillators, or simple mass–spring systems (each tuned to a different frequency), arranged in parallel (Methods, Modeling and Data Analysis, para. 1, Withnell); fig 1C of Withnell), with each branch comprising a stiffness, damping, and mass component (fig 1C of Withnell; Examiner notes that stiffness is C, damping is R, and mass is M), wherein the network represents mechanics of a tympanic membrane coupled to ossicles of an ear (fig 1C of Withnell).
Claim(s) 16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Allen et al. (US Patent Pub. No. 20150265189) hereinafter Allen, in view of Prieve (Prediction of Conductive Hearing Loss Using Wideband Acoustic Immittance – cited by Applicant), in view of Withnell (An Analysis of the Acoustic Input Impedance of the Ear), and further in view of Grais (Analysing wideband absorbance immittance in normal and ears with otitis media with effusion using machine learning – cited by Applicant).
Regarding Claim 16, Allen discloses a system for estimating hearing loss (systems, methods, and devices for characterizing ear canal acoustic impedance and reflectance by pole-zero fitting to determine ear drum impedance thereby assessing any middle ear pathologies from analyzing the ear drum impedance [0028]), comprising:
a device for obtaining an acoustic measurement from an ear canal (The one or more modules 217 may include a measurement module 220, calibration module 222, acoustic transmission module 224, acoustic reception module 226, control module 228, and acoustic signal processing module 230. [0035]; fig 2);
the device including a computer readable medium (a processor bank 210, storage device bank 215, one or more software applications, which may be executed by a processor form specifically-configured module devices 217, and one or more communication interfaces (235-250) [0035]; fig 2) configured to:
obtain the acoustic measurement from the ear canal (The one or more modules 217 may include a measurement module 220, calibration module 222, acoustic transmission module 224, acoustic reception module 226, control module 228, and acoustic signal processing module 230. [0035]; fig 2).
Allen fails to disclose a computer readable medium configured to:
model the acoustic measurement with an electric-analog model to obtain model outputs;
transforming the model output to a measured absorbance to determine an averaged absorbance over a frequency range converted to decibels;
and training a machine-learned network, wherein the training comprises:
acquiring measured hearing loss data;
fitting the parameters of the model such that the transformed model output correlates to the measured hearing data;
and identifying one or more classifiers of the transformed model output that provides an estimate of the hearing loss.
However, Prieve teaches a method of estimating hearing loss (the effectiveness of wideband acoustic immittance (WAI) and tympanometry in detecting conductive hearing loss (CHL) (abstract)), comprising:
obtaining an acoustic measurement from an ear canal (Three studies collected WAI in groups of adults with CHL whose etiologies were surgically confirmed. (Wideband Middle Ear Measures in Adults, para. 1));
transforming an output of the acoustic measurement to a measured absorbance to determine an averaged absorbance over a frequency range converted to decibels (Some studies reported wideband absorbance (A), which is the power absorbed by the outer/middle ear under ambient conditions and is computed as 1− |R|^2. Although Keefe and Simmons (2003) reported on the measure “transmittance,” the equation used was the same as that for A. Rosowski et al. (2012) and Nakajima et al. (2012) computed A and transformed their data to a dB scale by using the equation 10 × Log (A), and is denoted as AdB in this article. (Introduction, para. 3); The mean |R|2 and AdB for these participant groups are illustrated in Figure 4A, B, respectively.(Wideband Middle Ear Measures in Adults, para. 1); An alternative method for measuring the properties of the outer ear/middle ear system has emerged in which broadband stimuli are presented and responses measured using a carefully, acoustically described probe that allows calculation of acoustic admittance as well as a host of other physical measures, such as acoustic impedance, power reflectance (R2), and power absorbance. (Introduction, para. 2)).
It would have been obvious to one having ordinary skill in the art at the time of the effective filing date to have modified the system of Allen such that the computer readable medium is configured to the model output to a measured absorbance to determine an averaged absorbance over a frequency range converted to decibels, as taught by Prieve, because it would allow for the system to compute a measure that can be used to determine hearing loss. The combination of familiar elements is likely to be obvious when it does no more than yield predictable results. See KSR International Co. v. Teleflex Inc., 550 U.S. 398, 415-421, 82 USPQ2d 1385, 1395 – 97 (2007) (see MPEP § 2143, A.).
Allen in view of Prieve fails to teach a computer readable medium configured to:
model the acoustic measurement with an electric-analog model to obtain model outputs;
and training a machine-learned network, wherein the training comprises:
acquiring measured hearing loss data;
fitting the parameters of the model such that the transformed model output correlates to the measured hearing data;
and identifying one or more classifiers of the transformed model output that provides an estimate of the hearing loss.
However, Withnell teaches modeling an acoustic measurement (Sound pressure measurements were made in one ear of subjects aged 18–30 years, the location of measurement being near the isthmus. (Methods, Subject and Data Collection, para. 1)) with an electric-analog model to obtain a model output (The ear was modeled as a one-dimensional lossy transmission line terminated by a distributed load impedance (a non-rigid termination), applicable to plane wave sound propagation. The ear canal was represented by a lossy transmission line. (Methods, Modeling and Data Analysis, para. 1); This type of model captures well the acoustic input impedance of the middle ear. (Methods, under equation 29); Sound pressure measurements in the ear canal using an acoustically calibrated sound source provide for the derivation of the acoustic input impedance of the ear, providing a window into the acoustico-mechanical function of the ear. This study investigated the respective contributions of the ear canal, the middle ear, and the cochlea to the acoustic input impedance of the ear by modeling the ear as a one-dimensional lossy transmission line terminated by a distributed load impedance. (Discussion, para. 1); fig 1).
It would have been obvious to one having ordinary skill in the art at the time of the effective filing date to have modified the system of Allen in view of Prieve such that the computer readable medium is configured to model the acoustic measurement with an electric-analog model to obtain model outputs, as taught by Withnell, because it would allow for the derivation of the acoustic input impedance of the ear canal and impedance of the ear canal is related to middle-ear pathologies as evidenced by Voss et al. (Acoustic Mechanisms that Determine the Ear-Canal Sound Pressures Generated by Earphones). See Introduction, B., paragraph 1.
The modified system of Allen in view of Prieve in view of Withnell teaches transforming the model output to a measured absorbance to determine an averaged absorbance over a frequency range converted to decibels.
Allen in view of Prieve in view of Withnell fails to teach a computer readable medium configured to:
training a machine-learned network, wherein the training comprises:
acquiring measured hearing loss data;
fitting the parameters of the model such that the transformed model output correlates to the measured hearing data;
and identifying one or more classifiers of the transformed model output that provides an estimate of the hearing loss.
However, Grais teaches a method of estimating hearing loss (This study aimed to develop Machine Learning (ML) tools to identify the WAI absorbance characteristics across different frequency-pressure regions in the normal middle ear and ears with otitis media with effusion (OME) to enable diagnosis of middle ear conditions automatically. (Abstract)) comprising: training a machine learning network (Development of machine learning (ML) models for WAI classification (Materials and Methods, Methods, Development of machine learning (ML) models for WAI classification)), wherein the training comprises:
acquiring measured hearing loss data (A total of 672 WAI data were collected from patients and volunteers in five hospitals in Beijing, Guangzhou and Xuzhou, China. There were 423 ears from 242 participants with normal middle ear function (age range 1–68), and 249 ears with OME from 163 participants (age range 1–73 years). (Materials and Methods, Materials, Wideband absorbance immittance (WAI) data acquisition); Figure 1c shows a 2D image using the domains of frequency and pressure corresponding to the WAI data in Fig. 1a. (Materials and Methods, Methods, WAI measuring system and data pre-processing); Basic ML classifiers were used to process the 2D WAI images after interpolating the pressure axis (Materials and Methods, Methods, Development of machine learning (ML) models for WAI classification));
fitting parameters of a model such that a model output correlates to the measured hearing data (As indicated in section “Methods”, different ML classifiers were developed and examined to determine their ability to categorise middle ear function as normal or OME using the 2D frequency-pressure WAI images... To train the FNN and CNN models, the binary cross entropy cost function and Adam optimizer were used. Because the initialization of the FNNs and CNNs is important, each model was trained three times with different random initialization for each training, i.e., training three models with the same structure but with different initializations. (Results, Outputs from various classification models: accuracy, area under the ROC curve, F1 score, precision and recall for categorising middle ear function as normal or OME)); and
identifying one or more classifiers of the model output that provides an estimate of the hearing loss (Further statistical analysis at each frequency-pressure point showed 88% of data points (4782 out of 5457) to have significant differences in absorbance values between normal ears and OME ears (Wilcoxon rank sum test, Z = 3.04, p < 0.0005). (Results, WAI characteristics and statistical analysis of the normal middle ear condition compared to ears with OME); the results from the ML classifiers in this study exceed diagnostic performance in identifying normal and OME ear conditions in the primary care settings by General Practitioners (GP) or other healthcare professionals using traditional middle ear diagnostic tools (Discussion and future study, para. 2)).
It would have been obvious to one having ordinary skill in the art at the time of the effective filing date to have modified the system if Allen in view of Prieve in view of Withnell such that the computer readable medium is configured to: training a machine-learned network, wherein the training comprises: acquiring measured hearing loss data; fitting the parameters of the model such that the transformed model output correlates to the measured hearing data; and identifying one or more classifiers of the transformed model output that provides an estimate of the hearing loss, as taught by Grais, because training a machine learning network with known data associated with a disease to predict/estimate the degree or presence of the disease is well-understood, routine, and conventional activity in the art. Furthermore, all the claimed elements were known in the prior art and one skilled in the art could have combined the elements as claimed by known methods with no change in their respective functions, and the combination would have yielded nothing more than predictable results to one of ordinary skill in the art. See KSR International Co. v. Teleflex Inc., 550 U.S. 398, 415-421, 82 USPQ2d 1385, 1395 (2007) (see MPEP §§ 2143, A. and 2143.02).
The modified system of Allen in view of Prieve in view of Withnell and further in view of Grais teaches the training comprises: acquiring measured hearing loss data; fitting parameters of the model such that the transformed model output correlates to the measured hearing data; and identifying one or more classifiers of the transformed model output that provides an estimate of the hearing loss.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Lewis & Neely (Non-invasive estimation of middle-ear input impedance and efficiency – cited by Applicant) discloses a method to transform ear canal impedance to eardrum impedance. Sackmann et al. (Model-based hearing diagnostics based on wideband tympanometry measurements utilizing fuzzy arithmetic – cited by Applicant) discloses model-based hearing diagnostics based on wideband tympanometry measurements using fuzzy arithmetic. Ni et al. (Modelling Cochlear Mechanics) discloses different electric-analog models of the ear. Merchant et al. (Effect of Middle-Ear Pathology on High-Frequency Ear Canal Reflectance Measurements in the Frequency and Time Domains) discloses using computational modeling to obtain fitted parameter values in a model of the ear canal and middle canal to distinguish major conductive pathologies. Intracoustics (Wideband Absorbance in the Clinical Evaluation of Middle Ear Disorders, https://www.youtube.com/watch?v=D7cEyxWOTO4&t=34s) discloses how wideband tympanometry and absorbance is used to determine middle ear pathologies. Voss et al. (Acoustic Mechanisms that Determine the Ear-Canal Sound Pressures Generated by Earphones) discloses different electric-analog models for the ear canal and middle ear and use the models to predict how different conditions affect ear canal pressures.
The following is a reason of lack of prior art rejections:
Regarding Claim 6, none of the prior art teaches or suggests, either alone or in combination, averaged absorbance over a frequency range is compared to a pure tone average to obtain the estimated hearing loss, in combination with the other claimed elements.
Regarding Claim 21, none of the prior art teaches or suggests, either alone or in combination, machine- learned training including the steps of comparing ossicular loss level outputs to a pure tone average, in combination with the other claimed elements.
There is a lack of prior art rejections for claims 17-20 due to their dependence on claim 21.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JANKI M BAVA whose telephone number is (571)272-0416. The examiner can normally be reached Monday-Friday 9:00-6:00 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, Jason Sims can be reached at 571-272-7540. 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.
/JANKI M BAVA/Examiner, Art Unit 3791
/ETSUB D BERHANU/Primary Examiner, Art Unit 3791