# US 12,178,634 B2 · Electronic stethoscope and diagnostic algorithm > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,178,634 B2 - Document ID: US12178634B2 - Status: Granted - Kind: B2 - Application number: 18/632,981 - Filed: 2024-04-11 - Published: 2024-08-01 - Granted: 2024-12-31 - Earliest claimed: 2022-04-17 - Assignees: Korion Health Inc. - Applicants: Korion Health Inc. - Inventors: Galen Charles Pershing Kirkpatrick; Anna Li; Thomas Hastings Greer, IV; Akshaya Poorani Anand; Nicholas Chen; Eunice Chee-Kay Chan - Web page: https://patentgrep.com/patent/US12178634B2 ## CPC - A61B 7/04: Electric stethoscopes - H04R 1/46: Special adaptations for use as contact microphones, e.g. on musical instrument, on stethoscope (throat mountings H04R1/14) - A61B 5/0002: {Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network (endoradiosondes A61B5/07)} - A61B 5/7267: {involving training the classification device} - A61B 5/744: {Displaying an avatar, e.g. an animated cartoon character} - A61B 7/003: {Detecting lung or respiration noise} - A61B 90/08: {Accessories or related features not otherwise provided for} - G16H 40/67: for remote operation - G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems - G16H 50/70: for mining of medical data, e.g. analysing previous cases of other patients - A61B 5/743: {Displaying an image simultaneously with additional graphical information, e.g. symbols, charts, function plots} - A61B 2090/0807: {Indication means} - A61B 2562/0204: Acoustic sensors - A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D) - H04R: LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; ELECTRIC HEARING AIDS; PUBLIC ADDRESS SYSTEMS (producing sounds with frequency not determined by supply frequency G10K) - G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA ## Abstract Sounds produced by internal organs of the body can be used to monitor health conditions related to, for example, the heart and lungs. The present disclosure includes an electronic stethoscope that may be positioned by a user on locations of the body to record sounds from organs. The present disclosure also includes visual algorithms to guide positioning of the electronic stethoscope and audio diagnostic algorithms for providing analysis of recorded sounds. ## Claims ### Claim 1 A method of positioning a stethoscope at one or more heart and/or lung listening locations, the method comprising: (a) providing a live video feed of a user's torso; (b) determining, by a listening location estimation algorithm, the one or more heart and/or lung listening locations based on the live video feed; (c) displaying the live video feed on a video screen with the one or more heart and/or lung listening locations overlaid thereon; (d) providing an electronic stethoscope in a field of view of the live video feed, the electronic stethoscope comprising a visual indicator comprising a variably switching light-emitting device; (e) moving the electronic stethoscope within a field of view of the live video feed such that the visual indicator is in the vicinity of the one or more heart and/or lung listening locations; (f) placing the electronic stethoscope under an article of clothing of the user against the user's bare skin with the variably switching light-emitting device facing away from the user such that light transmitted by the variably switching light-emitting device passes through the article of clothing and is visible on the live video feed; and (g) rendering, on the live video feed displayed on the video screen, a shape overlapping with a live location of the visual indicator of the electronic stethoscope, the shape changing in color and/or shape to indicate when the electronic stethoscope is positioned correctly at one of the one or more heart and/or lung listening locations. ### Claim 2 (depends on 1) The method of claim 1, wherein determining, by the listening location estimation algorithm, the one or more heart and/or lung listening locations based on the live video feed comprises using a pose estimation algorithm, the pose estimation algorithm outputting key points of a pose of the user, the key points comprising the locations of at least the left shoulder, the hips, and the right shoulder of the user, and wherein determining the one or more heart and/or lung listening locations further comprises: determining vertical locations using a fixed percentage of a shoulder-to-hip distance, and determining horizontal locations using a fixed percentage of a shoulder-to-shoulder distance. ### Claim 3 (depends on 1) The method of claim 1, the method after step (g) further comprising prompting the user, by the listening location estimation algorithm, to move the stethoscope to align the shape overlapping with the visual indicator with the overlaid one or more heart and/or lung listening locations. ### Claim 4 (depends on 3) The method of claim 3, wherein prompting the user comprises at least one of: displaying a message prompt, displaying an arrow pointing in the direction the user should move the stethoscope, and changing a color of the shape overlapping with the visual indicator when the user is in the wrong location to a different color than when the user is in correct location. ### Claim 5 (depends on 1) The method of claim 1, wherein the method further comprises: (h) recording a duration of heart and/or lung sounds at each of the heart valve and/or lung listening locations; (i) providing the sound recordings to a trained audio classification algorithm; (j) repeating steps (a) through (j) until a sound recording at each of the heart valve and/or lung listening locations has been recorded; and (k) outputting, by the trained audio classification algorithm, a classification of each of the sound recordings corresponding to at least one of normal heart function, normal lung function, one or more of a plurality of heart conditions, or one or more of a plurality of lung conditions. ### Claim 6 (depends on 5) The method of claim 5, wherein the plurality of heart conditions comprises innocent murmur, aortic stenosis, and mitral valve prolapse, and wherein the plurality of lung conditions are associated with abnormal lung sounds comprising crackles, wheezes, rhonchi, stridor, rales, and pleural friction rubs. ### Claim 7 (depends on 1) The method of claim 1, wherein the one or more variably switching light-emitting devices comprise one or more light-emitting diodes each emitting light of a visible wavelength or a near-infrared wavelength, wherein the one or more light-emitting diodes each follow a controlled switching program that switches the one or more light-emitting diodes on and off in an ordered pattern at a controllable repetition frequency of between about 2 Hz and about 30 Hz, wherein the light-emitting device emits light at a wavelength between about 400 nm and about 1000 nm, and wherein rendering, on the live video feed displayed on the video screen, a shape overlapping with a live location of the visual indicator comprises using a light tracking algorithm that uses multiple frames captured over time to determine the number of frames in a light blink cycle of the visual indicator, thereby identifying the location of the visual indicator based on the controllable repetition frequency. ### Claim 8 (depends on 1) The method of claim 1, wherein the one or more heart and/or lung listening locations comprise one or more of an aortic valve area, a pulmonic valve area, a tricuspid valve area, and a mitral valve area, and wherein the lung listening locations comprise locations one or more locations near apexes of lungs, upper lobes of lungs, middle lobes of lungs, and lower lobes of lungs, on left and right sides of the user's front and back torso. ### Claim 9 (depends on 1) The method of claim 1 further comprising, after step (a) and before step (b): superimposing, in real time, multiple zones comprising multiple color masks on the video screen, the multiple zones comprising a first region, a second region, and a third region, thereby indicating to the user if the user's body as a whole is too close or too far from the video screen, or alternatively, if the user's body as a whole is positioned correctly relative to the video screen. ### Claim 10 (depends on 9) The method of claim 9, wherein the first region corresponds to a first zone in which the user's head is expected to be located, wherein the second region corresponds to a second zone in which the user's torso is expected to be located, and wherein the third region corresponds to a third zone in which the user's lower body is expected to be located. ### Claim 11 (depends on 10) The method of claim 10 further comprising: displaying a first indication on the video screen if the user's body is incorrectly positioned within each of the first, second, and third regions, and displaying a second indication on the video screen if the user's body is correctly positioned within each of the first, second, and third regions. ### Claim 12 An electronic stethoscope comprising: a chest piece comprising: a hollow bell portion; a membrane portion covering an end of the bell portion; a stem portion attached to an outer circumferential wall of the hollow bell portion; a shoulder portion attached to the stem portion; and a microphone compartment attached to the shoulder portion; a microphone disposed in the microphone compartment; a visual indicator disposed on an exterior of the chest piece; and an electronic data connection from the microphone, wherein at least a portion of each of the hollow bell portion, the stem portion, the shoulder portion, and the microphone compartment form a single, continuous component composed of a polymer material and formed via a single manufacturing process. ### Claim 13 (depends on 12) The electronic stethoscope of claim 12, wherein the electronic stethoscope further comprises a microprocessor and an analog-to-digital converter, wherein the visual indicator comprises one or more light-emitting devices, and wherein the microphone comprises a pulse density modulation (PDM) micro-electromechanical systems (MEMS) microphone and/or a lavalier microphone. ### Claim 14 (depends on 12) The electronic stethoscope of claim 12, wherein the membrane comprises a flexible polymer sheet composed of a material elected from the group consisting of acetate, polyester, polyethylene terephthalate (PET), polyethylene, polypropylene, polystyrene, epoxy fiberglass, resin, thermoset plastic, polyvinyl chloride (PVC), and polytetrafluoroethylene (PTFE), and wherein the membrane comprises a thickness in a range from about 0.01 inches to about 0.05 inches. ### Claim 15 (depends on 12) The electronic stethoscope of claim 12, wherein the hollow bell portion, the stem portion, the shoulder portion, and the microphone compartment are composed of a plastic material selected from the group consisting of polylactic acid (PLA), acrylonitrile butadiene styrene (ABS), and polyethylene terephthalate glycol-modified (PET-G), wherein the hollow bell portion comprises a concave face comprising an inverted conical portion, and wherein the chest piece further comprises an internal bore disposed within the concave face of the hollow bell portion and extending to the microphone compartment. ### Claim 16 (depends on 12) The electronic stethoscope of claim 12, comprising a microphone seal disposed circumferentially around, and in contact with, an interior wall of a lumen of the microphone compartment, the microphone seal further in contact with an exterior surface of the microphone such that air does not pass between the interior wall of the lumen of the microphone compartment and the exterior surface of the microphone. ### Claim 17 (depends on 16) The electronic stethoscope of claim 16, wherein the microphone seal is composed of at least one of silicone, rubber, adhesive, resin, epoxy, polymer, wax, acrylic, rubber cement, thermoplastic adhesive, hot-melt adhesive, polytetrafluoroethylene, polyurethane, polycarbonate, polypropylene, nylon, nitrile, neoprene, polyvinyl chloride, fluorocarbon, and fluorosilicone. ### Claim 18 A method of training a machine learning algorithm to identify heart and/or lung sounds comprising: obtaining heart and/or sound recordings corresponding to known heart and/or lung conditions and corresponding to normal healthy heart and/or lung function; obtaining non-heart-and/or-lung sound recordings of sounds; providing the heart and/or lung sound recordings and non-heart-and/or-lung sound recordings to an audio classifier model; segmenting the recordings via at least one of frequency, amplitude, and duration; inputting the segmented recordings into a U-Net neural network; preprocessing the segmented recordings, via the U-Net neural network, into a spectrogram for frequency equivariance, thereby producing corrected segmentation recordings; outputting the corrected segmentation recordings; and using the audio classifier model to train the machine learning algorithm to distinguish between the heart and/or lung sound recordings and non-heart-and/or-lung sound recordings, wherein the heart and/or lung sound recordings are obtained from recordings performed by an electronic stethoscope and/or a microphone, and wherein the audio classifier model comprises a pre-trained audio neural network (PANN), a dataset of known audio recordings, information regarding health conditions and demographics of patients with known heart and/or lung conditions, and information regarding healthy patients. ### Claim 19 (depends on 18) The method of claim 18, wherein non-heart-and/or-lung sound recordings comprises sounds such as speech, vehicle traffic, dogs barking, children crying, noise, and music, and wherein providing sound recordings to the audio classifier model occurs on a regular repeating schedule and comprises providing new sound recordings and new known health information. ### Claim 20 (depends on 18) The method of claim 18, wherein segmenting the recordings via at least one of frequency, amplitude, and duration comprises identifying at least two portions of each recording, the method further comprising identifying any other indicative sound within each recording, wherein the corrected segmentation recordings comprise a timeline indicating when each type of feature is present in each recording. ### Claim 21 (depends on 20) The method of claim 20, wherein the at least two portions of each recording comprise: for heart recordings, a first portion corresponding to a systolic portion of a heartbeat, and a second portion corresponding to diastolic portion of a heartbeat, and for lung recordings, a first portion corresponding to an inhalation, and a second portion corresponding to an exhalation.