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 without traverse of Invention I, claims 1-6 in the reply filed on 11/12/2025 is acknowledged.
Claims 7-10 are withdrawn from further consideration pursuant to 37 CFR 1.142(b) as being drawn to a nonelected Invention, there being no allowable generic or linking claim. Election was made without traverse in the reply filed on 11/12/2025.
Applicant is reminded that upon the cancelation of claims to a non-elected invention, the inventorship must be corrected in compliance with 37 CFR 1.48(a) if one or more of the currently named inventors is no longer an inventor of at least one claim remaining in the application. A request to correct inventorship under 37 CFR 1.48(a) must be accompanied by an application data sheet in accordance with 37 CFR 1.76 that identifies each inventor by his or her legal name and by the processing fee required under 37 CFR 1.17(i).
Claims 1-6 are currently under examination.
Claim Objections
Claim 2 objected to because of the following informalities:
In Claim 2, “each of auscultation” (line 3) should read –each of a plurality of auscultation-
Appropriate correction is required.
Claim Rejections - 35 USC § 112
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 3-5 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 written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention.
Claim 3 recites the limitation “the detecting includes detecting abnormality in the lung sounds of each of the auscultation positions at the determination object time of the subject, on a basis of a normal model of each of the auscultation positions that is learned by using the lung sound data of each of the auscultation positions at the time of discharge from the hospital of the subject”, where the applicant’s specification lacks sufficient detail in regards to the structure of the “normal model” for each of the auscultation positions. The applicant’s specification does state “The normal model of each auscultation position may be a single model or a plurality of models obtained by machine learning from different viewpoints…” (Par. 45 of applicant’s spec.), and further recites “As a generated model, Gaussian mixture model (GMM), one-class SVM, denoising auto-encoder with bidirectional LSTM that is a type of deep neural network (DNN), k-nearest neighbor algorithm (kNN), or the like may be used.” (Par. 43 of applicant’s spec.), “The learning model can be generated in advance through machine learning using a machine learning algorism such as a neural network by using time-series acoustic signals including various lung sounds as teacher data.” (Par. 61 of applicant’s spec.). However, simply reciting the existence of machine learning and providing an example of the architecture does not provide sufficient detail as to the actual model itself. For example, the applicant has not provided sufficient detail in regards to the exact weights, biases, or layers used for the model itself. As such, the claim is rejected.
Claim 4 recites the limitation “the probability being obtained from the normal model when the lung sound data at the determination object time of the subject is input into the normal model learned by using the lung sounds data of the auscultation positions of the subject at the time of discharge from the hospital in which the auscultation observation describes that abnormality in the lung sounds exists”, which lacks sufficient detail within the applicant’s specification in regards to the manner in which the probability is calculated. The applicant’s specification does state “lung sound data into the normal model171 previously generated and stored corresponding to the focused auscultation position, and acquires the probability that the lung sound data is abnormal lung sounds from the normal model171. Then, when the used normal model171 is the type1, the lung sound abnormality detection means163 compares the probability of abnormal lung sounds with a preset threshold…” (Par. 66 of applicant’s spec.), which indicates the use of a model to generate a probability. The model is indicated within the specification as “The normal model of each auscultation position may be a single model or a plurality of models obtained by machine learning from different viewpoints…” (Par. 45 of applicant’s spec.), and further recites “As a generated model, Gaussian mixture model (GMM), one-class SVM, denoising auto-encoder with bidirectional LSTM that is a type of deep neural network (DNN), k-nearest neighbor algorithm (kNN), or the like may be used.” (Par. 43 of applicant’s spec.), “The learning model can be generated in advance through machine learning using a machine learning algorism such as a neural network by using time-series acoustic signals including various lung sounds as teacher data.” (Par. 61 of applicant’s spec.). However, simply reciting the existence of machine learning and providing an example of the architecture does not provide sufficient detail as to the actual model itself. For example, the applicant has not provided sufficient detail in regards to the exact weights, biases, or layers used for the model itself. As such, the claim is rejected.
Claim 5 recites the limitation “using a normal model learned by using the lung sound data that is confirmed to be normal by the medical specialist, in place of the normal model learned by using the lung sound data of the auscultation position of the subject at the time of discharge from the hospital in which the auscultation observation describes that there is abnormality in the lung sounds”, where the applicant’s specification lacks sufficient detail in regards to the structure of the “normal model” for reach normal model. The applicant’s specification indicates “when, when the used normal model171 is the type1, the lung sound abnormality detection means163 compares the probability of abnormal lung sounds with a preset threshold, and when the probability exceeds the threshold, the lung sound abnormality detection means163 determines that the lung sound data is abnormal lung sounds, while when the probability is equal to or lower than the threshold, determines that the lung sounds data is normal lung sounds. On the other hand, when the used normal model171 is the type2,” (Par. 66 of applicant’s spec.), which indicates the presence of differing model types. The applicant’s specification further states “The normal model of each auscultation position may be a single model or a plurality of models obtained by machine learning from different viewpoints…” (Par. 45 of applicant’s spec.), and further recites “As a generated model, Gaussian mixture model (GMM), one-class SVM, denoising auto-encoder with bidirectional LSTM that is a type of deep neural network (DNN), k-nearest neighbor algorithm (kNN), or the like may be used.” (Par. 43 of applicant’s spec.), “The learning model can be generated in advance through machine learning using a machine learning algorism such as a neural network by using time-series acoustic signals including various lung sounds as teacher data.” (Par. 61 of applicant’s spec.). However, simply reciting the existence of machine learning and providing an example of the architecture does not provide sufficient detail as to the actual model itself. For example, the applicant has not provided sufficient detail in regards to the exact weights, biases, or layers used for the model itself. As such, the claim is rejected.
Claims 4-5 are dependent on claim 3, and as such are also rejected.
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 3-5 rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 3 recites the limitation “the detecting includes detecting abnormality in the lung sounds of each of the auscultation positions at the determination object time of the subject, on a basis of a normal model of each of the auscultation positions that is learned by using the lung sound data of each of the auscultation positions at the time of discharge from the hospital of the subject”, which fails to effectively define the metes and bounds of the claim as it is unclear as to the structure of the “normal model” for each of the indicated positions. The corresponding structure is defined within the applicant’s specification as “The normal model of each auscultation position may be a single model or a plurality of models obtained by machine learning from different viewpoints…” (Par. 45 of applicant’s spec.), “As a generated model, Gaussian mixture model (GMM), one-class SVM, denoising auto-encoder with bidirectional LSTM that is a type of deep neural network (DNN), k-nearest neighbor algorithm (kNN), or the like may be used.” (Par. 43 of applicant’s spec.), and “The learning model can be generated in advance through machine learning using a machine learning algorism such as a neural network by using time-series acoustic signals including various lung sounds as teacher data.” (Par. 61 of applicant’s spec.). However, it is unclear as to the structure of each of the indicated model that accomplishes the indicated function. For example, what are the exact weights, biases, or layers for each model? As such, the claim is indefinite as the applicant has failed to effectively define the metes and bounds of the claim. For examination purposes, this will be interpreted as any generic algorithm.
Claim 3 recites the limitation “a basis of a normal model of each of the auscultation positions that is learned by using the lung sound data of each of the auscultation positions at the time of discharge from the hospital of the subject”, which fails to effectively define the metes and bounds of the claim as it is unclear as to the amount of models present. The claim itself states “a basis of a normal model of each of the auscultation positions that is learned”, where the portion “a basis of a normal model of each of the auscultation positions” is indicative of a plurality of models. However, the inclusion of the phrase “that is learned” is presented in such a manner that it appears that it is now a single model. How many models are present? The applicant’s specification states “The normal model of each auscultation position may be a single model or a plurality of models obtained by machine learning from different viewpoints.” (Par. 45 of applicant’s spec.), which does not provide further clarification. As such, the claim is indefinite as the applicant has failed to effectively define the metes and bounds of the claim. For examination purposes, this will be interpreted as any number of models present (Par. 45 of applicant’s spec.).
Claim 4 recites the limitation “the probability being obtained from the normal model when the lung sound data at the determination object time of the subject is input into the normal model…”, which fails to effectively define the metes and bounds of the claim as it is unclear as to the manner in which the probability obtained from the normal model is generated. The applicant’s specification does state “lung sound data into the normal model171 previously generated and stored corresponding to the focused auscultation position, and acquires the probability that the lung sound data is abnormal lung sounds from the normal model171. Then, when the used normal model171 is the type1, the lung sound abnormality detection means163 compares the probability of abnormal lung sounds with a preset threshold, and when the probability exceeds the threshold, the lung sound abnormality detection means163 determines that the lung sound data is abnormal lung sounds…” (Par. 66 of applicant’s spec.), which indicates the use of a model to generate a probability. The model is indicated within the specification as “The normal model of each auscultation position may be a single model or a plurality of models obtained by machine learning from different viewpoints…” (Par. 45 of applicant’s spec.), and further recites “As a generated model, Gaussian mixture model (GMM), one-class SVM, denoising auto-encoder with bidirectional LSTM that is a type of deep neural network (DNN), k-nearest neighbor algorithm (kNN), or the like may be used.” (Par. 43 of applicant’s spec.), “The learning model can be generated in advance through machine learning using a machine learning algorism such as a neural network by using time-series acoustic signals including various lung sounds as teacher data.” (Par. 61 of applicant’s spec.). However, it is unclear as to the structure of each of the indicated model that accomplishes the indicated function. For example, what are the exact weights, biases, or layers for the model? As such, the claim is indefinite as the applicant has failed to effectively define the metes and bounds of the claim. For examination purposes, the model will be interpreted as any generic algorithm capable of producing a probability.
Claim 5 recites the limitation “using a normal model learned by using the lung sound data that is confirmed to be normal by the medical specialist, in place of the normal model learned by using the lung sound data of the auscultation position of the subject at the time of discharge from the hospital in which the auscultation observation describes that there is abnormality in the lung sounds”, which fails to effectively define the metes and bounds of the claim as it is unclear as to the structure of the “normal model”. The applicant’s specification does state “The normal model of each auscultation position may be a single model or a plurality of models obtained by machine learning from different viewpoints…” (Par. 45 of applicant’s spec.), and further recites “As a generated model, Gaussian mixture model (GMM), one-class SVM, denoising auto-encoder with bidirectional LSTM that is a type of deep neural network (DNN), k-nearest neighbor algorithm (kNN), or the like may be used.” (Par. 43 of applicant’s spec.), “The learning model can be generated in advance through machine learning using a machine learning algorism such as a neural network by using time-series acoustic signals including various lung sounds as teacher data.” (Par. 61 of applicant’s spec.). However, it is unclear as to the structure of the indicated model that accomplishes the indicated function. For example, what are the exact weights, biases, or layers for each model? As such, the claim is indefinite as the applicant has failed to effectively define the metes and bounds of the claim. For examination purposes, the model will be interpreted as any generic algorithm.
Claims 4-5 are dependent on claim 3, and as such are also rejected.
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 are rejected under 35 U.S.C. 101 because the claimed invention is directed towards a judicial exception without significantly more. These claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception or that are sufficient to amount to significantly more than the judicial exception.
Step 1 of the subject matter eligibility test
Claim 1 is directed towards a device, which describes one of the four statutory categories of patentable subject matter.
Step 2A of the subject matter eligibility test
Prong 1: Claims 1 recites the abstract idea of a mental process as follows:
“store..” “…time-series acoustic signals including lung sounds at a time of discharge from hospital of a subject who is a heart failure patient, as reference signals”, “acquire time-series acoustic signals including lung sounds at a determination object time after the discharge from the hospital of the subject, as determination object signals”, and “detect abnormality in the lung sounds from the determination object signals on a basis of the reference signals”.
The storing time-series acoustic signals including lung sounds at a time of discharge from hospital of a subject who is a heart failure patient, as reference signals, acquiring time-series acoustic signals including lung sounds at a determination object time after the discharge from the hospital of the subject, as determination object signals, and detecting abnormality in the lung sounds from the determination object signals on a basis of the reference signals can be practically performed by the human mind, with the aid of a pen and paper, but for performance on a generic processor, in a computer environment, or merely using the computer as a tool to perform the steps.
A person of ordinary skill in the art could reasonably store time series signals of a heart failure patient as reference signals based with a generic computer based on being a handed a piece of paper with time series signals. A person of ordinary skill in the art could reasonably acquire time series signals that include lung sounds as determination signals with a generic computer based on being handed a piece of paper with the time series signals. A person of ordinary skill in the art could reasonably detect an abnormality in lung sounds based on having a piece of paper with determination object signals and reference signals mentally or with a generic computer.
There is currently nothing to suggest an undue level of complexity in the storing, acquiring, or detecting. Therefore, a person would be able to practically be able to perform the detecting, acquiring, and storing steps mentally or with the aid of pen and paper.
Prong Two: Claims 1 does not recite additional elements that integrate the mental process into a practical application. Therefore, the claims are “directed to” the mental process. The additional elements merely:
Recite the words “apply it” or an equivalent with the judicial exception, or include instructions to implement the abstract idea on a computer, or merely use the computer as a tool to perform the abstract idea (e.g., a memory with instructions, a processor coupled to memory) and
For claim 1. The additional elements merely serve to gather data to be used by the abstract idea. The processor and memory are merely used as a pre-solution step of necessary data gathering to be used by the abstract idea. There is no practical application because the abstract idea is not applied, relied on, or used in a meaningful way. The processing that is performed remains in the abstract realm, i.e. the gathered data is not used for a treatment or meaningful purpose. Additionally, there is no overall improvement to existing technology present. The mental process merely functions on generic computer elements that do not change the functionality of the device itself. Therefore, the additional elements, alone or in combination, do not integrate the abstract idea into a practical application.
Step 2B of the subject matter eligibility test for Claim 1.
Per the Berkheimer requirement, the additional elements are well-understood, routine, and conventional. For example,
Memory with instructions and a processor connected to memory as disclosed by Fairbrothers (US Pub. No. 20140088988) hereinafter Fairbrothers, “Each computer may be well known to those skilled in the art and may include a display, a central processor, a system memory, and a system bus that couples various system components including the system memory to the central processor unit. The system bus may be any of several types of bus structures including a memory bus or memory controller, a peripheral bus, and a local bus using any of a variety of bus architectures…” (Par. 22) and Haskell (US Pub. No. 20030233252) hereinafter Haskell “Information device 4000 may include well-known components such as one or more network interfaces 4010, one or more processors 4020, one or more memories 4030 containing instructions 4040, and/or one or more input/output ("I/O") devices 4050, all interconnected in a known manner…” (Par. 45).
are all well-understood, routine, and conventional.
Claims 2-6 do not include additional elements, alone or in combination that are sufficient to amount to significantly more than the judicial exception (i.e., an inventive concept) as all of the elements are directed to the further describing of the abstract idea, pre-solution activities, and computer implementation.
The dependent claims merely further define the abstract idea and are, therefore, directed to an abstract idea for similar reasons: they merely further describe the abstract idea:
the reference signals include lung sound data of each of auscultation positions at the time of discharge from the hospital of the subject (Claim 2),
the determination object signals include lung sounds of each of the auscultation positions at the determination object time of the subject (Claim 2),
detecting abnormality in the lung sounds from the determination object signals on a basis of the reference signals, for each of the auscultation positions (Claim 2),
the detecting includes detecting abnormality in the lung sounds of each of the auscultation positions at the determination object time of the subject, on a basis of a normal model of each of the auscultation positions that is learned by using the lung sound data of each of the auscultation positions at the time of discharge from the hospital of the subject (Claim 3) (Examiner's Note: A person of ordinary skill in the art could reasonably train a model based on being handed a piece of paper lung sound data at different positions with a generic computer),
the reference signals include an auscultation observation of each of the auscultation positions at the time of discharge from the hospital of the subject (Claim 4),
when probability of existence of abnormality in the lung sounds is equal to or lower than a threshold, the probability being obtained from the normal model when the lung sound data at the determination object time of the subject is input into the normal model learned by using the lung sounds data of the auscultation positions of the subject at the time of discharge from the hospital in which the auscultation observation describes that abnormality in the lung sounds exists, detecting includes determining that there is abnormality in the lung sound data at the determination object time of a same type as a type of the abnormality at the time of discharge from the hospital (Claim 4) (Examiner's Note: A person of ordinary skill in the art could reasonably make a determination that there is an abnormality based with a generic computer based on having lung sound data and probability measurement),
when the probability exceeds the threshold, determining that there is abnormality of a type different from the type of the abnormality at the time of discharge from the hospital or there is no abnormality (Claim 4),
the detecting includes, when it is confirmed by a medical specialist that the lung sound data, determined to have abnormality in the lung sounds of the type different from the type at the time of discharge from the hospital or determined to have no abnormality, is normal lung sound data, using a normal model learned by using the lung sound data that is confirmed to be normal by the medical specialist, in place of the normal model learned by using the lung sound data of the auscultation position of the subject at the time of discharge from the hospital in which the auscultation observation describes that there is abnormality in the lung sounds (Claim 5) (Examiner's Note: A person of ordinary skill in the art could reasonably use a normal model with a generic computer in place of a different model based on receiving a piece of paper with a confirmation),
the acquiring includes dividing the time-series acoustic signals including the lung sounds at the determination object time after the discharge from the hospital of the subject into time-series acoustic signals in an inspiratory and expiratory section and time-series acoustic signals in a pause section (Claim 6),
acquiring digital time-series acoustic signals in the inspiratory and expiratory section as the determination object signals (Claim 6).
Per the Berkheimer requirement, the additional elements are well-understood, routine, and conventional.
Taken alone or in combination, the additional elements do not integrate the judicial exception into a practical application at least because the abstract idea is not applied, relied on, or used in a meaningful way. The additional elements do not add anything significantly more than the abstract idea. The collective functions of the additional elements merely provide computer/electronic implementation and processing, data gathering, and no additional elements beyond those of the abstract idea. There is no indication that the combination of elements improves the functioning of a mobile device, output device, improves technology other than the technical field of the claimed invention, etc. Therefore, the claims are rejected as being directed to non-statutory subject matter.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The claims are generally directed towards a lung analysis device. The device includes a processor configured to store time series acoustic lung signals of a patient being discharged from a hospital as reference signals, acquire lung sounds at a time after the patient is discharged, and detect an abnormality in the lung sounds between the signals.
Claim(s) 1-2 is/are rejected under 35 U.S.C. 103 as being unpatentable over Zhang (US Pub. No. 20110009760) hereinafter Zhang, and further in view of Song (US Pub. No. 20130237862) hereinafter Song.
Regarding claim 1, Zhang teaches A lung sound analysis device comprising (Par. 9 (system))(Par. 13-15, (Respiration circuitry to collect information)) (Par. 33):
program instructions (Par. 13-15, (circuitry to collect information)); and
a processor (Par. 13-15 (processor connected to circuitry)), wherein the processor (Par. 13-15 (processor connected to circuitry)) is configured to execute the program instructions to:
store, time-series acoustic signals including lung sounds at a time of discharge from hospital of a subject who is a heart failure patient, as reference signals (Par. 74, 80, “During at least a portion of the patient's stay in the hospital (a period(s) between times 501 and 503), physiologic data is collected for purposes of developing a baseline(s) and threshold(s) that are used by a hospital readmission alert algorithm of the present invention.” (baseline)) (Par. 83, “involves collecting 360 respiration data and activity data for a heart failure patient during hospitalization and a time after discharge from the hospital, and measuring 362 a median respiration rate (MedRR) and a maximum respiration rate (MaxRR) using the collected respiration data. During at least a portion of the patient's stay in the hospital, respiration data is collected for purposes of developing baselines for the MedRR, MaxRR, and patient activity, and their respective thresholds that are used by a hospital readmission alert algorithm of the present invention.”) (Par. 51,61, (respiratory data));
acquire time-series acoustic signals including lung sounds at a determination object time after the discharge from the hospital of the subject, as determination object signals (Par. 75, “At or near the time 503 the patient has been discharged, the hospital readmission alert algorithm initiates collection and analysis of post-discharge physiologic data acquired for the patient. In the illustrative example of FIG. 6, physiologic data shown as Physiologic Data-1 through Physiologic Data-N are collected for the patient during a readmission alert analysis window 505. In general terms, the readmission alert analysis window 505 defines a duration of time following patient discharge from the hospital for collection and analysis of the discharged patient's physiologic data that is sufficiently long to detect early onset of worsening heart failure post-discharge…”) (Par. 83, “involves collecting 360 respiration data and activity data for a heart failure patient during hospitalization and a time after discharge from the hospital, and measuring 362 a median respiration rate (MedRR) and a maximum respiration rate (MaxRR) using the collected respiration data. During at least a portion of the patient's stay in the hospital, respiration data is collected for purposes of developing baselines for the MedRR, MaxRR, and patient activity, and their respective thresholds that are used by a hospital readmission alert algorithm of the present invention.”) (Par. 51,61 (respiratory data)); and
detect abnormality in the lung sounds from the determination object signals on a basis of the reference signals (Par. 83, “involves collecting 360 respiration data and activity data for a heart failure patient during hospitalization and a time after discharge from the hospital, and measuring 362 a median respiration rate (MedRR) and a maximum respiration rate (MaxRR) using the collected respiration data. During at least a portion of the patient's stay in the hospital, respiration data is collected for purposes of developing baselines for the MedRR, MaxRR, and patient activity, and their respective thresholds that are used by a hospital readmission alert algorithm of the present invention.”) (Par. 84, “The methodology illustrated in FIG. 8 further involves analyzing 363 the MedRR and MaxRR for a change in these data relative to their respective baselines and thresholds, and detecting 365 deterioration of the patient's heart failure status based at least in part on detecting an acute deleterious change in the MedRR and MaxRR indicative of an abnormality in MedRR and MaxRR and an indication that the patient is not engaged in patient activity. A readmission alert is generated 367 in response to detecting the acute deleterious change in the MedRR and MaxRR and an indication that the patient is not engaged in patient activity”).
Zhang fails to explicitly disclose a memory containing program instructions; a processor coupled to the memory; and store, in the memory.
However, Zhang does disclose a processor coupled to respiration information circuitry that executes program instructions (Par. 13-15 (processor and respiration circuitry)), and wherein the processor causes the circuitry to collect and analyze respiration data (Par. 13-15).
Song teaches a memory containing program instructions (Par. 56, (memory with instructions)) (Par. 101);
a processor coupled to the memory (Par. 53, “Processor 44 or signal analyzer 46 may store the heart sound signal parameters and lung sound signal parameters in memory 48.”) (Par. 56 (memory with instructions that are executed by the processor)) (Par. 101);
and store, in the memory (Par. 53, “Processor 44 or signal analyzer 46 may store the heart sound signal parameters and lung sound signal parameters in memory 48…”)(Par. 101).
Zhang and Song are considered to be analogous art to the claimed invention as they are involved with measurement and analysis of patient data.
Therefore, it would have been obvious to a person of ordinary skill in the art to modify the device of Zhang with that of Song to include a memory containing program instructions; a processor coupled to the memory; and store, in the memory through the combination of references as differing computational structures and implementations are known in the art (Song (Par. 56, 101)), and it would have yielded the predictable result of providing the exact computational structures needed for the device.
Regarding claim 2, modified Zhang further discloses the reference signals include lung sound data auscultation position at the time of discharge from the hospital of the subject (Zhang (Par. 74, 80, “During at least a portion of the patient's stay in the hospital (a period(s) between times 501 and 503), physiologic data is collected for purposes of developing a baseline(s) and threshold(s) that are used by a hospital readmission alert algorithm of the present invention.” (baseline)) (Par. 83, “involves collecting 360 respiration data and activity data for a heart failure patient during hospitalization and a time after discharge from the …”) (Par. 51,61, (respiratory data))),
the determination object signals include lung sounds of the auscultation position at the determination object time of the subject (Zhang Par. 75, “At or near the time 503 the patient has been discharged, the hospital readmission alert algorithm initiates collection and analysis of post-discharge physiologic data acquired for the…”) (Par. 83, “involves collecting 360 respiration data and activity data for a heart failure patient during hospitalization and a time after discharge from the hospital, and measuring 362...”) (Par. 51,61 (respiratory data))), and
the detecting includes detecting abnormality in the lung sounds from the determination object signals on a basis of the reference signals, for the auscultation position (Zhang (Par. 83, “involves collecting 360 respiration data and activity data for a heart failure patient during hospitalization and a time after discharge from the hospital, and measuring 362 a median respiration rate (MedRR) and a maximum respiration rate (MaxRR) using the collected respiration data. During at least …”) (Par. 84, “The methodology illustrated in FIG. 8 further involves analyzing 363 the MedRR and MaxRR for a change in these data relative to their respective baselines and thresholds, and detecting 365 deterioration of the patient's heart failure…”).
Modified Zhang fails to explicitly disclose signals of each of auscultation positions and detecting for each of the auscultation positions.
However, Song further teaches signals of each of auscultation positions and detecting for each of the auscultation positions (Par. 30, “Consistent with the present disclosure, a correlation between heart and/or lung sounds are used to monitor pulmonary hypertension...” “...the use of an external patch may allow for a patient to be monitored continuously or at regular intervals without the need for invasive procedures to determine pulmonary arterial blood pressure.”) (Par. 35 (measurements at different locations))(Par. 57, “Telemetry module 42 includes any suitable hardware, firmware, software or any combination thereof for communicating with another device, such as external patch 16...” “...an indication of a change in disease state of the heart, or a change in programming to change one or more therapy parameters. The indication may be based heart and/or lung sounds”) (Par. 86, 93 (monitoring lung sounds)).
Therefore, it would have been obvious to a person of ordinary skill in the art to modify the device of Zhang and Song with that of Song to include signals of each of auscultation positions and detecting for each of the auscultation positions through the combination of references as it would have yielded the predictable result of improving data quality by providing additional data at different measurements sites.
Claim(s) 3-4 and 6 is/are rejected under 35 U.S.C. 103 as being unpatentable over Zhang in view of Song as applied to claims 1 and 2 above, and further in view of Karankevich (US Pub. No. 20210145306) hereinafter Karankevich.
Zhang and Song teach the device of claim 2 above.
Regarding claim 3, modified Zhang further discloses the detecting includes detecting abnormality in the lung sounds of each of the auscultation positions at the determination object time of the subject on a basis of a model that is learned by using the lung sound data at the time of discharge from the hospital of the subject (Zhang (Par. 83, “involves collecting 360 respiration data and activity data for a heart failure patient during hospitalization and a time after discharge from the hospital, and measuring 362 a median respiration rate (MedRR) and a maximum respiration rate (MaxRR) using the collected respiration data. During at least …”) (Par. 84, “The methodology illustrated in FIG. 8 further involves analyzing 363 the MedRR and MaxRR for a change in these data relative to their respective baselines and thresholds, and detecting 365 deterioration of the patient's heart failure…”) (Par. 74, 80, “During at least a portion of the patient's stay in the hospital (a period(s) between times 501 and 503), physiologic data is collected for purposes of developing a baseline(s) and threshold(s) that are used by a hospital readmission alert algorithm of the present invention.” (baseline)) (Par. 51,61, (respiratory data)) (Par. 74, 75, 116 (algorithm that includes data at time of discharge))).
Modified Zhang fails to explicitly disclose a model of each of the auscultation positions that is learned by using the lung sound data of each of the auscultation positions.
Zhang does disclose the use of machine learning algorithms (Zhang (Par. 116)).
However, Karankevich teaches a model of each of the auscultation positions that is learned by using the lung sound data of each of the auscultation positions (Par. 40-41 (sound capture points sent to the machine learning model)) (Par. 44 (trained model)) (Par. 5 (trained)) (Par. 11 (sound records captured at one or more points at successive times)).
Zhang, Song, and Karankevich considered to be analogous art to the claimed invention as they are involved with measurement and analysis of patient data.
Therefore, it would have been obvious to a person of ordinary skill in the art to modify the device of Zhang and Song with that of Karankevich to include a model of each of the auscultation positions that is learned by using the lung sound data of each of the auscultation positions through the substitution of algorithms as differing algorithms are known in the art (Zhang (Par. 116)) and it would have yielded the predictable result of allowing for the classification of sound types (Karankevich (Par. 46)).
Regarding claim 4, modified Zhang further discloses the reference signals include an auscultation observation of at the time of discharge from the hospital of the subject (Zhang (Par. 74, 80, “During at least a portion of the patient's stay in the hospital (a period(s) between times 501 and 503), physiologic data is collected for purposes of developing a baseline(s) and threshold(s) that are used by a hospital readmission alert algorithm of the present invention.” (baseline)) (Par. 83, “involves collecting 360 respiration data and activity data for a heart failure patient during hospitalization and a time after discharge from the hospital, and measuring 362 a median respiration rate (MedRR) and a maximum respiration rate (MaxRR) using the collected respiration data. During at least a portion of the patient's stay in the hospital, respiration data is collected for purposes of developing baselines for the MedRR, MaxRR, and patient activity, and their respective thresholds that are used by a hospital readmission alert algorithm of the present invention.”) (Par. 51,61, (respiratory data))), and
when existence of abnormality in the lung sounds is equal to or lower than a threshold (Zhang (Par. 116 (meets alert threshold)), obtained from the normal model when the lung sound data at the determination object time of the subject is input into the normal model learned by using the lung sounds data of the auscultation positions of the subject at the time of discharge from the hospital in which the auscultation observation describes that abnormality in the lung sounds exists (Zhang (Par. 116 (output of model triggers readmission alert)) (Par. 34 (disease))) (Zhang (Par. 74, 80 (baseline)) (Par. 83 (threshold and baseline) (Par. 51,61, (respiratory data))), detecting includes determining that there is abnormality in the lung sound data at the determination object time of a same type as a type of the abnormality at the time of discharge from the hospital (Zhang (Par. 83, “involves collecting 360 respiration data and activity data for a heart failure patient during hospitalization and a time after discharge from the hospital, and measuring 362 a median respiration rate (MedRR) and a maximum respiration rate (MaxRR) using the collected respiration data. During at least …”) (Par. 84, “The methodology illustrated in FIG. 8 further involves analyzing 363 the MedRR and MaxRR for a change in these data relative to their respective baselines and thresholds, and detecting 365 deterioration of the patient's heart failure…”)) (Par. 34 (disease progression and regression))).
Modified Zhang fails to explicitly disclose the auscultation positions.
However, Song further teaches auscultation positions (as indicated in claim 2 above).
Therefore, it would have been obvious to a person of ordinary skill in the art to modify the device of Zhang, Song, and Karankevich with that of Song to include auscultation positions for the reasoning as indicated in claim 2 above.
Modified Zhang fails to explicitly disclose when probability of existence of abnormality in the lung sounds is equal to or lower than a threshold, the probability being obtained from the normal model, when the probability exceeds the threshold, determining that there is abnormality of a type different from the type of the abnormality at the time of discharge from the hospital or there is no abnormality.
However, Karankevich further teaches when probability of existence of abnormality in the lung sounds is equal to or lower than a threshold (Karankevich (Par. 46, (probability of each class compared to one another)), the probability being obtained from the normal model (Karankevich (Par. 46, “the machine learning model can generate, for each incoming captured sound, probabilities for each class; the class with the highest probability is construed as the result of the classification. In some cases, the sound classes are specified with purported certainty…”) (Par. 26, “Respiratory sound data can be associated with different phases of breathing (ventilation), for example, the two main respiratory phases: inspiration and expiration. Respiratory sound data also can be associated with various respiratory sound classes. Respiratory sound classes can in turn be associated with various respiratory conditions. Respiratory sound classes include normal inspiration and expiration (vesicular, bronchial, tracheal), and abnormal classes: wheezing, rhonchi, fine crackles, coarse crackles, and normal breathing.”)),
when the probability exceeds the threshold (Karankevich (Par. 46, (probability of each class compared to one another, in the case when normal breathing is highest)), determining that there is abnormality of a type different from the type of the abnormality at the time of discharge from the hospital or there is no abnormality (Karankevich (Par. 46, “the machine learning model can generate, for each incoming captured sound, probabilities for each class; the class with the highest probability is construed as the result of the classification. In some cases, the sound classes are specified with purported certainty…”) (Par. 26, “Respiratory sound data can be associated with different phases of breathing (ventilation), for example, the two main respiratory phases: inspiration and expiration. Respiratory sound data also can be associated with various respiratory sound classes. Respiratory sound classes can in turn be associated with various respiratory conditions. Respiratory sound classes include normal inspiration and expiration (vesicular, bronchial, tracheal), and abnormal classes: wheezing, rhonchi, fine crackles, coarse crackles, and normal breathing.”).
Therefore, it would have been obvious to a person of ordinary skill in the art to modify the device of Zhang, Song, and Karankevich with that of Karankevich to include when probability of existence of abnormality in the lung sounds is equal to or lower than a threshold, the probability being obtained from the normal model, when the probability exceeds the threshold, determining that there is abnormality of a type different from the type of the abnormality at the time of discharge from the hospital or there is no abnormality through the combination of references as differing classification techniques are known in the art (Karankevich (Par. 43,46)) and it would have yielded the predictable result of classifying the output and providing additional respiratory information (Karankevich (Par. 26,28, 46)).
Zhang and Song teach the device of claim 1 above.
Regarding claim 6, modified Zhang fails to explicitly disclose the limitations of the claim.
However, Karankevich teaches the acquiring includes dividing the time-series acoustic signals including the lung sounds at the determination object time after the discharge from the hospital of the subject into time-series acoustic signals in an inspiratory and expiratory section and time-series acoustic signals in a pause section (Karankevich (Par. 38 (respiratory sounds))) (Karankevich (Par. 26 (respiratory sound data))(Karankevich (Par. 131-138 (inspiratory, expiratory and pause)), and acquiring digital time-series acoustic signals in the inspiratory and expiratory section as the determination object signals (Karankevich (Par. 38 (respiratory sounds))) (Karankevich (Par. 26 (respiratory sound data))(Karankevich (Par. 131-138 (inspiratory, expiratory and pause)).
Therefore, it would have been obvious to a person of ordinary skill in the art to modify the device of Zhang and Song with that of Karankevich to include teaches the acquiring includes dividing the time-series acoustic signals including the lung sounds at the determination object time after the discharge from the hospital of the subject into time-series acoustic signals in an inspiratory and expiratory section and time-series acoustic signals in a pause section, and acquiring digital time-series acoustic signals in the inspiratory and expiratory section as the determination object signals as inspiratory and expiratory sections are known respiratory phases (Karankevich (Par. 26)) and it would have yielded the predictable result of allowing for the analysis of different disease types (Karankevich (Par. 26)).
Claim(s) 5 is/are rejected under 35 U.S.C. 103 as being unpatentable over Zhang in view of Song and Karankevich as applied to claim 4 above, and further as referenced by Baron (US Pub. No. 20210350930) hereinafter Baron.
Zhang, Song, and Karankevich teach the device of claim 4 above.
Regarding claim 5, modified Zhang fails to explicitly disclose the limitations of the claim.
However, Karankevich further teaches the detecting includes, when it is confirmed by a medical specialist that the lung sound data, determined to have abnormality in the lung sounds of the type different from the type at the time of discharge from the hospital or determined to have no abnormality, is normal lung sound data, using a normal model learned by using the lung sound data that is confirmed to be normal by the medical specialist (Karankevich (Par. 46, “the machine learning model can generate, for each incoming captured sound, probabilities for e