DETAILED ACTION
Applicant’s arguments, filed 04/14/2026, have been fully considered. The following rejections and/or objections are either reiterated or newly applied. They constitute the complete set presently being applied to the instant application. Applicant has amended their claims, filed 04/14/2026, and therefore rejections newly made in the instant office action have been necessitated by amendment.
Applicant canceled claims 2-6, 8, 10, 13, 17-18, and 20-22. Applicant added claims 27-36. Claims 1, 7, 9, 11-12, 14-16, 19, and 23-36 are pending and hereby under examination.
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 .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 05/14/2026 has been entered.
Claim Objections
Claims 1, 14-15, 19, and 24 are objected to because of the following informalities:
Claim 1, line 5 should read “the vibration transducer and the inertial sensor for transmitting …”.
Claim 1, lines 54-56 should read “processing the tracked longitudinal trajectories with a machine learning model to predict one or more medical interventions, determine a timing for initiation of the one or more medical interventions, and scheduling one or more medical interventions in advance …”.
Claim 14, line 2 should read “communication with a membrane arranged on a bell …” for proper antecedent basis.
Claim 15, lines 12-13 should read “wherein the one or more additional signals comprise …”.
Claim 15, line 23 should read “relocating the digital stethoscope on the body …”.
Claim 19, lines 6 and 11 should refer to “at least one additional sensor”.
Claim 19, line 14 should refer to the “digital stethoscope”.
Claim 24, line 3-4 should refer to the “at least one of a video and image …”.
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 1, 7, 9, 11-12, 14, 25, and 27-35 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.
Claims 1, 7, 9, 11-12, 14, 25, and 27-35 are directed towards a genus encompassing an unbounded set of physiological conditions in the step of assigning confidence values/probabilities associated with presence of a physiological condition.
The specification, however, discloses physiological conditions as conditions of the cardiovascular and respiratory systems. Such conditions include “valve surgery, mechanical valve replacements, fistulas, and peripheral artery disease” (Page 11, lines 5-6), “coronary artery disease” (Page 11, lines 19-20), or “pneumonia or COVID-19” (Page 19, lines 26-28).
The specification does not, for example, disclose assigning confidence values/probabilities to conditions of the brain, the eyes, or the stomach. The entire genus of “physiological conditions” is not satisfied through sufficient written description; rather, it appears the disclosure satisfies the written description requirement for the genus of cardiovascular and/or respiratory physiological conditions. For examination purposes, the claims will be interpreted such that a physiological condition is a cardiovascular and/or respiratory condition. Examiner suggests narrowing the physiological condition limitation to a “cardiovascular and/or respiratory condition”, or the like.
Claims 1, 7, 9, 11-12, 14, 25, and 27-35 are directed towards a genus encompassing an unbounded set of machine learning models in the step of processing tracked longitudinal trajectories with a machine learning model to predict medical interventions, determine a timing for initiation of medical interventions, and scheduling one or more interventions.
The specification discloses broad examples of machine learning models such as “artificial intelligence (AI), neural networks, regression, Markov models, Gaussian mixture models, support vector machines, random forest, and other machine learning (ML) algorithms”. However, the specification does not describe in detail how all of these types of machine learning models are used.
For example, the specification describes that an AI is trained to predict future interventions and optimum timing, and the processing results show when future interventions may be needed. The AI processes the sounds to infer, for example, the current state of a catheter. The AI uses measurement history and/or typical progressions, as well as the current measured sounds, to predict when the catheter’s stenosis will exceed prescribed conditions and schedule any necessary interventions to remedy the predicted condition (Page 10, line 29 – Page 11, line 6).
There is no disclosure of using a Markov model, a Gaussian mixture model, a random forest, and/or a support vector machine. Further, while neural networks are disclosed, the description does not disclose, for example, using a convolutional neural network. The entire genus of “machine learning models” is not satisfied through sufficient written description. For examination purposes, the “machine learning model” will be interpreted as an AI model trained to perform the intervention prediction, timing determination, and intervention scheduling steps. However, Examiner suggests narrowing the type of machine learning model used to perform the function in the claim.
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.
Claim 1, 7, 9, 11-12, 14-16, 19, and 23-36 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 15, it is unclear if the enhanced “diagnostically relevant portions of the digitized sound” is the same as the “clinically valuable portions of the digitized sound” that are stored, the “diagnostically meaningful information”, and the “processed, segmented, and/or diagnostically enhanced portions of the digitized sound”. Additionally, it is unclear if these types of digitized sound are the same, similar, or different than the “physiologically relevant signal components” within the digitized sound as recited in claim 33. Applicant should clarify the difference, if any, or use the same terminology between the portions of digitized sound.
Further, the step of computing diagnostic scores becomes unclear with regard to the different recitations of the digitized sound as it is unclear how many types of digitized sound are determined. Is the digitized sound processed separately from being weighted and filtered? Are these two steps separate from the steps of segmenting the digitized sound? Are all of these steps performed separately, or do they build off of each other in a specific order? For examination purposes, the claim will be interpreted as separate steps, and at least one of the digitized sound types identified above are used to compute diagnostic scores. Claims 7, 9, 11-12, 14, 16, 19, and 23-36 are also rejected due to their dependence on claims 1 and 15.
Regarding claims 1 and 15, the claims require assigning confidence values/probabilities associated with presence of a physiological condition. It is unclear what type or types of physiological conditions are claimed based on the data collected. Per the specification, it appears the physiological conditions are limited to conditions of the cardiovascular and respiratory system. Such conditions include “valve surgery, mechanical valve replacements, fistulas, and peripheral artery disease” (Page 11), “coronary artery disease” (Page 11), or “pneumonia or COVID-19” (Page 19). Examiner suggests narrowing the physiological condition limitation to a “cardiovascular and/or respiratory condition”, or the like. For examination purposes, the claims will be interpreted such that a physiological condition is a cardiovascular and/or respiratory condition. Claims 7, 9, 11-12, 14, 16, 19, and 23-36 are also rejected due to their dependence on claims 1 and 15.
Regarding claims 1 and 15, the claims require processing tracked longitudinal trajectories with a machine learning model to predict medical interventions and to determine a timing for initiation of medical interventions, and scheduling one or more interventions. It is unclear what type or types of machine learning models are claimed. Per the specification, Applicant points to broad examples of machine learning models such as “artificial intelligence (AI), neural networks, regression, Markov models, Gaussian mixture models, support vector machines, random forest, and other machine learning (ML) algorithms”.
However, the specification describes that an AI is trained predict future interventions and optimum timing, and the processing results show when future interventions may be needed. The AI processes the sounds to infer, for example, the current state of a catheter. The AI uses the history of measurements and/or typical progressions, as well as the current sounds, to predict when the catheter’s stenosis will exceed prescribed conditions and schedule any necessary interventions to remedy the predicted condition. There is no disclosure of using a Markov model, a Gaussian mixture model, a random forest, and/or a support vector machine. Further, while neural networks are disclosed, the description does not disclose, for example, using a convolutional neural network.
For examination purposes, the “machine learning model” will be interpreted as an AI model trained to perform the intervention prediction, timing determination, and intervention scheduling steps. However, Examiner suggests narrowing the type of machine learning model used to perform the function in the claim. Claims 7, 9, 11-12, 14, 16, 19, and 23-36 are also rejected due to their dependence on claims 1 and 15.
Response to Arguments
Applicant’s arguments, see page 14, filed 04/14/2026, with respect to the drawings objection have been fully considered and are persuasive. Applicant has corrected the typographical error of Fig. 6. The objection to the drawings has been withdrawn.
Applicant’s arguments, see page 14, filed 04/14/2026, with respect to the specification objection have been fully considered and are persuasive. Upon further consideration of the specification objection, the Applicant appears to have support for the alleged new matter added to the specification filed 12/22/2025. Figure 1 depicts supplemental compute resources 207. The specification on page 6, lines 18-19 state that the “supplemental compute resources can be maintained on networked machines or can be provisioned in the cloud 208”. Further, the specification on page 7, lines 22-28 state algorithms and methods for diagnosis, detection, and other processing for use by the supplemental compute resources. Figure 1 and the identified specification lines appear to support the added matter to the specification filed 12/22/2025. If the Applicant filed a new specification with the paragraphs added in the specification filed 12/22/2025, an objection to the specification would not be raised. The objection of the specification has been withdrawn.
Applicant’s arguments, see page 15, filed 04/14/2026, with respect to the claim objections have been fully considered and are persuasive. Applicant has canceled the claims. The objection of the claims has been withdrawn. However, new objections have been applied.
Applicant’s arguments, see page 15, filed 04/14/2026, with respect to the 35 U.S.C. §112(a) rejections have been fully considered and are persuasive. Upon further consideration, the Applicant appears to have support for the alleged new matter added to the specification and claims filed 12/22/2025. Figure 1 depicts supplemental compute resources 207. The specification on page 6, lines 18-19 state that the “supplemental compute resources can be maintained on networked machines or can be provisioned in the cloud 208”. Further, the specification on page 7, lines 22-28 state algorithms and methods for diagnosis, detection, and other processing for use by the supplemental compute resources. Figure 1 and the identified specification lines appear to support the added matter to the specification filed 12/22/2025. If the Applicant filed a new specification with the paragraphs added in the specification filed 12/22/2025 and added the limitations previously rejected in the claims, such as to a “processor” or a “non-transitory machine-readable medium”, a 112(a) rejection of the claims would not be raised. The rejection of the claims has been withdrawn. However, new rejections have been applied.
Applicant’s arguments, see page 15, filed 04/14/2026, with respect to the 35 U.S.C. §112(b) rejections have been fully considered and are persuasive. Applicant has amended the claims to remove “optionally”. Applicant has amended the independent claims to recite that inertial data is collected from an inertial sensor. Applicant has canceled the rejected claims of 6 and 18. Therefore, the rejections of the claims has been withdrawn. However, new rejections have been applied.
Applicant’s arguments, see pages 15-17, filed 04/14/2026, with respect to the 35 U.S.C. §103 rejections have been fully considered and are persuasive. Examiner agrees that the combination of Rinderknecht and Kapoor do not teach all of the newly added limitations of independent claims 1 and 15, specifically the analysis, integration, and segmentation of the digitized sound with the inertial data. The rejection of the claims has been withdrawn. See below.
Prior Art
The prior art of record includes Rinderknecht (US 20210386309), Kapoor (US 20170049339), Jeevannavar (US 20210030390), Yoo (US 8764655), Bates (US 20190279768), and Atallah (US 20160235306).
Rinderknecht discloses a digital stethoscope (Fig. 2, handheld device 20) with a vibration transducer that receives and digitizes sound (Paragraphs 0079 and 0083; Paragraph 0071, “The amplified motion can therefore subsequently be recorded through any number of non-invasive transducers such as piezoelectric, capacitive, piezoresistive, optical, acoustic, ultrasound or electromagnetic”), and a transmitter in operable communication with the vibration transducer for transmitting the digitized sound (Paragraph 0054) wherein the digital stethoscope is configured to be placed on the body of the patient in a location to obtain sound (Fig. 2, placed against the carotid artery).
The system further includes a user interface device in operable communication with the transmitter of the digital stethoscope, the user interface device comprising a display and being configured to receive the digitized sound transmitted by the transmitter (Fig. 3, smartphone unit 200). The system is configured to perform the following steps:
receiving the digitized sound via the transmitter (Paragraph 0055, “As illustrated, smartphone 200 communicates with/between sensor device 100 employing signals 120/220 as in “paired” BLUETOOTH devices or via another protocol. The smartphone may receive information corresponding to a hemodynamic signal as further treated below. Such a signal may be stored and/or processed via connection with the Internet—as in so-called Cloud 202 computing”), from the digital stethoscope positioned at multiple anatomical sites over multiple time points (Figs. 14A-C; Paragraphs 0089-0093, wherein the method includes sensing at multiple locations);
determining a direction to move the digital stethoscope for relocation on the body of the patient (Paragraphs 0090-0093);
transmitting to the user interface device one or more commands viewable by the user on the display regarding the direction and position to move the digital stethoscope for relocation on the body of the patient (Paragraphs 0090-0093, wherein the user is directed by device feedback to a location to obtain adequate signal);
applying adaptive weighting, including time-varying and source-component dependent weights, and frequency filtering to enhance diagnostically relevant portions of the digitized sound (Paragraph 0023 and 0081, wherein different filters may be used to obtain relevant portions of the sounds, such as low-pass filtering to yield the true pulse pressure waveform, high-pass filtering to yield the true embedded frequency or heart sound; Applicant defines using the weights to filter the data, see page 12 of the specification. Examiner interprets using multiple filters to generate different types of waveforms from the sound data as “adaptive weighting” to obtain diagnostically relevant portions of the digitized sound);
performing automatic segmentation of the digitized sound (Paragraph 0086, “any cardiac cycle detection and/or segmentation of heart waveforms is potentially aided by the use of Embedded Frequencies”; Paragraph 0102)
storing clinically valuable portions of the digitized sound and discarding non-informative data to optimize memory use and focus on diagnostically meaningful information (Paragraph 0055, “The smartphone may receive information corresponding to a hemodynamic signal as further treated below. Such a signal may be stored and/or processed via connection with the Interne”; Paragraphs 0080-0081, wherein the hemodynamic waveform is filtered; Examiner interprets the filter as removing non-informative data);
wherein the one or more commands for moving the digital stethoscope comprise direct queues that visually indicate the direction to move the stethoscope (Paragraph 0091).
Rinderknecht fails to disclose an inertial sensor for generating inertial data and performing analysis with the inertial data.
Rinderknecht further fails to disclose the steps of:
integrating the inertial data with the digitized sound to generate time-varying probability signals indicative of cardiac activity, stethoscope relocation, non-target body sounds, and other background body sounds;
performing automatic segmentation of the digitized sound on the basis of sounds and a time-varying probability of stethoscope relocation based on inertial data;
computing diagnostic scores, tracking diagnostic scores over time to form longitudinal trajectories and displaying temporal trends, wherein the longitudinal trajectories assess progression or changes in patient condition, generating alerts based on progression patterns observed in longitudinal trajectories,
assigning confidence values or probabilities associated with presence of a physiological condition to the segmented portions of the digitized sound;
augmenting datasets derived from the digitized sound and the inertial data with user-entered data, and processing the tracked longitudinal trajectories with a machine learning model to predict medical interventions and determine a timing for initiation of the medical interventions, and scheduling one or more interventions in advance.
Kapoor discloses a diagnostic system stethoscope (Fig. 16) wherein the sensor sleeve includes an accelerometer (Paragraph 0068; Fig. 15). Kapoor further discloses measuring a myocardial performance index (Paragraph 0075), a systolic performed index (Paragraph 0077), and scoring data to track the data and send notification of data trends (Paragraph 0098). However, the system of Kapoor fails to integrate the inertial data with digitized sound, segment the digitized sound on the bases on sounds and inertial data, augmenting the datasets, and/or processing the tracked longitudinal trajectories with a machine learning model to predict medical interventions, determine timing for initiation of a medical intervention, and scheduling an intervention.
Jeevannavar discloses a stethoscope configured to analyze electronic sound waveforms, wherein a machine learning model determines contributions of attributes to diagnostic and/or analytic output 9Paragraphs 0050 and 0079-0080). Jeevannavar fails to cure the deficiencies of Rinderknecht discussed above.
Yoo discloses a stethoscope wherein a display depicts images on a body to where the stethoscope sensor should be located. Yoo fails to cure the deficiencies of Rinderknecht discussed above.
Bates discloses a system of utilizing a video and image of the body of the patient with a pose estimation model to define a coordinate system utilizing the shoulders and tracking/estimating position of the stethoscope on a display relative to the patient (Figs. 4-5, Paragraphs 0031, 0084, and 0099). Bates fails to cure the deficiencies of Rinderknecht discussed above.
Lastly, Atallah discloses a system for non-invasive thermal monitoring to take multiple temperatures of a patient and generate a temperature map to determine a core temperature (Figs. 4A-B; Paragraphs 0039-0044).
As such, the prior art of record fails, alone or in combination, to teach or suggest all of the limitations of independent claims 1 and 15.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to NOAH MICHAEL HEALY whose telephone number is (703)756-5534. The examiner can normally be reached Monday - Friday 8:30am - 5:30pm 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.
/NOAH M HEALY/Examiner, Art Unit 3791
/JASON M SIMS/Supervisory Patent Examiner, Art Unit 3791
Prosecution Insights