Systems and methods for dictation with a digital stethoscope
Inventors
Venkatraman, Subramaniam • Childs, Michael • Freschl, Dan • Brower, Theo • Palaniappan, Shanmugam Muruga • Landgraf, Connor
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-12380973-B1
Publication Date
2025-08-05
Expiration Date
Abstract
The present description relates to methods and systems for a medical dictation. In one example, a stethoscope includes a first microphone positioned to capture physiological sounds of a patient, a second microphone positioned to capture ambient sounds, one or more processors, and memory storing instructions executable by the one or more processors to: during a stethoscope mode, obtain a first signal from the first microphone and a second signal from the second microphone, process the first signal to capture a physiological sound signal, including performing noise cancellation on the first signal based on the second signal, and transmit the physiological sound signal to an external computing device and/or a speaker of the stethoscope; and during a dictation mode, obtain the second signal from the second microphone, process the second signal to capture a voice signal, and transmit the voice signal to the external computing device.
Core Innovation
A dictation stethoscope includes a body having a top surface and a bottom surface, a first microphone positioned inside the body to capture physiological sounds by translating vibrations due to movement of a diaphragm into a first signal, and a second microphone positioned at the top surface to capture ambient sounds surrounding the dictation stethoscope. The dictation stethoscope operates in both a stethoscope mode and a dictation mode.
In the stethoscope mode, the processor obtains the first signal from the first microphone and a second signal from the second microphone, processes the first signal to capture a physiological sound signal, and performs noise cancellation on the first signal based on the second signal. In the stethoscope mode, the dictation stethoscope transmits the physiological sound signal to an external computing device and/or a speaker of the dictation stethoscope.
In the dictation mode, the dictation stethoscope obtains the second signal from the second microphone, processes the second signal to capture a voice signal, and transmits the voice signal to the external computing device. During the dictation mode, the first microphone is deactivated, and the processing includes downsampling the first signal such that the physiological sound signal has a first sampling rate lower than a second sampling rate of the voice signal.
A system architecture extends the dictation stethoscope to an analysis system that receives the physiological sound recording and the voice recording. The analysis system automatically generates patient notes that include a voice transcription of the voice recording and the physiological sound recording, saves the patient notes in long-term storage and/or pushes the patient notes to an electronic medical record (EMR) system, and supports generating exam findings based on ECG signal and/or physiological sound signal for incorporation into patient summary notes.
Claims Coverage
The independent claims cover a dictation stethoscope, a system using the dictation stethoscope with an analysis system, and a method for operating the dictation stethoscope across stethoscope mode and dictation mode. The inventive features center on dual-microphone capture, mode-dependent processing, noise cancellation, downsampling, deactivation of the internal microphone in dictation mode, and integration with automatic note generation and storage/EMR push.
Dual-mode dictation stethoscope with internal physiological microphone and top ambient microphone
A dictation stethoscope with a first microphone positioned to capture physiological sounds inside the body from a diaphragm at the bottom surface, and a second microphone positioned at the top surface to capture ambient sounds around the dictation stethoscope, wherein one or more processors and memory operate in both a stethoscope mode and a dictation mode.
Noise-cancel physiological sound capture in stethoscope mode using ambient microphone signal
During a stethoscope mode, obtain the first signal from the first microphone and a second signal from the second microphone, process the first signal to capture a physiological sound signal including performing noise cancellation on the first signal based on the second signal, and transmit the physiological sound signal to an external computing device and/or a speaker of the dictation stethoscope.
Voice capture in dictation mode using ambient microphone and deactivating the internal microphone
During a dictation mode, obtain the second signal from the second microphone, process the second signal to capture a voice signal, and transmit the voice signal to the external computing device, wherein during the dictation mode, the first microphone is deactivated.
Downsampling physiological sound relative to voice in dictation operation
Process the first signal including downsampling the first signal such that the physiological sound signal has a first sampling rate lower than a second sampling rate of the voice signal.
System with device capture and analysis system generating notes and saving/pushing to an EMR
A system including a medical device operating in a stethoscope mode and a dictation mode, and an analysis system configured to receive the physiological sound recording and the voice recording, automatically generate patient notes that include a voice transcription of the voice recording and the physiological sound recording, and save the patient notes in long-term storage and/or push the patient notes to an electronic medical record (EMR) system.
Automatic note generation including voice transcription and physiological sound recording
An analysis system configured to automatically generate patient notes that include a voice transcription of the voice recording and the physiological sound recording.
Deactivation of internal microphone in dictation mode with noise-cancel and downsampling operation
A method operating a dictation stethoscope in a stethoscope mode including obtaining a first signal from a first microphone and a second signal from a second microphone, processing the first signal including performing noise cancellation on the first signal based on the second signal, transmitting the physiological sound signal, and then operating in dictation mode including obtaining the second signal, processing the second signal to form a voice signal, transmitting the voice signal, wherein during the dictation mode the first microphone is deactivated, and wherein processing the first signal includes downsampling the first signal such that the physiological sound signal has a first sampling rate lower than a second sampling rate of the voice signal.
Across the independent claims, the core coverage is the mode-dependent processing of signals from two microphones in a dictation stethoscope: noise-canceling physiological sound acquisition in stethoscope mode using the ambient microphone signal, and voice acquisition in dictation mode using the ambient microphone while deactivating the internal microphone, combined with downsampling of physiological audio relative to voice. The system and method claims further extend this to an analysis system that automatically generates patient notes with voice transcription and physiological sound recording, and then saves or pushes notes to an EMR.
Stated Advantages
Captures a physiological sound recording with noise cancellation during stethoscope mode.
Captures a voice signal during dictation mode by using the ambient microphone while deactivating the first microphone.
Reduces physiological sound sampling rate relative to the voice signal.
Automatically generate patient notes including a voice transcription and physiological sound recording.
Saves patient notes in long-term storage and/or pushes patient notes to an EMR system.
Documented Applications
Automatic generation of patient notes that include voice transcription of the voice recording and the physiological sound recording.
Saving patient notes in long-term storage and/or pushing patient notes to an electronic medical record (EMR) system.
Generating and incorporating exam findings based on ECG signal and/or physiological sound signal into patient summary notes derived from the voice signal.
Interested in licensing this patent?