Electronic stethoscope and diagnostic algorithm
AssigneeKorion Health Inc.
InventorsGalen Charles Pershing Kirkpatrick, Anna Li, Thomas Hastings Greer, IV, Akshaya Poorani Anand, Nicholas Chen, Eunice Chee-Kay Chan
Life of this patent
Estimating the term…
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.
Claims21
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;
- (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;
- and
- (f) 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.
An electronic stethoscope comprising:
- a chest piece comprising a hollow bell portion and a membrane portion covering an end of the bell portion;
- a microphone disposed in the chest piece;
- a visual indicator disposed on an exterior of the chest piece;
- and
- an electronic data connection from the microphone.
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;
- 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.
Dependencies are inferred from the claim text.