Methods and systems for automated clinical workflows
Inventors
Blair, Richard N. • Prince, John • Maidens, John • Bora, Niladri • Crouch, Tyler • Crivelli-Decker, Jordan • Venkatraman, Subramaniam • Zorko, John • Bobra, Neraj
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-12249419-B2
Publication Date
2025-03-11
Expiration Date
Abstract
Various methods and systems are provided for an automated clinical exam workflow. In one example, method comprises performing a signal quality check of an electronic stethoscope at a first recording location on a subject, recording physiological data for an exam at the first recording location via the electronic stethoscope in response to the signal quality check satisfying a quality threshold, and outputting a signal quality alert in response to the signal quality check not satisfying the quality threshold. In this way, clinically relevant data may be obtained with reduced user effort and fewer manual inputs.
Core Innovation
The invention provides an automated clinical auscultation workflow using an electronic stethoscope that performs a signal quality check on an initial sample of physiological data at a first recording location on a subject. The signal quality check includes selecting a model specific to the first recording location from a plurality of models for a plurality of recording locations and evaluating a quality of the initial sample using only the selected model via a machine learning algorithm. Further physiological data for an exam at the first recording location is recorded in response to the signal quality check satisfying a quality threshold, and a signal quality alert is output in response to the signal quality check not satisfying the quality threshold.
The workflow supports placement guidance and confirmation using augmented reality. Visually guiding a placement of the electronic stethoscope via augmented reality prior to performing a signal quality check allows the method to proceed once the placement of the electronic stethoscope is confirmed at a desired recording location. The guidance uses real-time images, a placement indicator, and confirmation based on overlap and/or threshold-distance criteria, and corrective alerts are output when placement confirmation is not satisfied.
A system embodiment evaluates a quality of a signal recorded by the electronic stethoscope based on a recording location, wirelessly transmits the recorded signal to an external computing device only when the quality is greater than a threshold, and discontinues transmission when the quality decreases below the threshold. The system uses a recording-location-specific model selection from a plurality of models and evaluates the quality using only the selected model via a machine learning algorithm, and it may include visually confirming stethoscope placement using live images obtained by the external computing device before evaluating the quality of the recorded signal.
Claims Coverage
The independent claims cover three main inventive areas: (1) location-specific machine-learning signal quality checks that gate recording and trigger signal quality alerts; (2) augmented-reality placement guidance that is used before the location-specific signal quality check; and (3) an auscultation system that evaluates location-specific signal quality and conditionally wirelessly transmits or discontinues transmission based on a threshold.
Location-specific signal quality check gating recording and alerting
Performing a signal quality check of an initial sample of physiological data from an electronic stethoscope at a first recording location, selecting a model specific to the first recording location from a plurality of models and evaluating quality using only the selected model via a machine learning algorithm; recording further physiological data for an exam at the first recording location in response to the signal quality check satisfying a quality threshold; and outputting a signal quality alert in response to the signal quality check not satisfying the quality threshold.
Augmented reality placement guidance prior to location-specific signal quality evaluation
While operating the electronic stethoscope in a first mode, visually guiding a placement of the electronic stethoscope via augmented reality prior to performing a signal quality check; and responsive to confirming placement at a desired recording location, performing the signal quality check including selecting a model specific to the desired recording location from a plurality of models and evaluating a quality of a signal recorded by the electronic stethoscope using only the selected model via a machine learning algorithm.
Location-specific quality evaluation with conditional wireless transmission
Evaluating a quality of a signal recorded by the electronic stethoscope based on a recording location; wirelessly transmitting the recorded signal to an external computing device in response to the quality of the signal being greater than a threshold; and discontinuing transmission in response to the quality decreasing below the threshold, wherein evaluating quality includes selecting a model specific to the recording location from a plurality of models and evaluating the quality using only the selected model via a machine learning algorithm.
Across the independent claims, the core claim coverage is directed to machine-learning evaluation of signal quality using recording-location-specific models, using that evaluation to gate further recording and output a signal quality alert, operate after augmented-reality placement confirmation, and conditionally wirelessly transmit or discontinue transmission based on a quality threshold.
Stated Advantages
Automated recording of further physiological data for an exam only when the signal quality check satisfies a quality threshold.
Outputting a signal quality alert when the signal quality check does not satisfy the quality threshold.
Conditional wireless transmission of the recorded signal to an external computing device only when evaluated quality is greater than a threshold, and discontinuing transmission when quality decreases below the threshold.
Visually guiding placement via augmented reality prior to performing the signal quality check to support confirmation at a desired recording location.
Documented Applications
Synchronous or asynchronous remote medical examinations using a clinical auscultation workflow with an electronic stethoscope and external computing device interfaces.
An auscultation exam with multiple prescribed recording locations, including iterative guidance and repeated signal quality checking and alert behavior.
Medical exam workflows that use augmented reality to guide stethoscope placement prior to signal quality checking.
Interested in licensing this patent?