Back to results
US 12,635,892 B2Granted
Non-invasive cardiac health assessment system and method for training a model to estimate intracardiac pressure data
AssigneeAcorai AB
InventorFilip Ludwig Peters
Life of this patent
Estimating the term…
Abstract
The present disclosure relates to cardiac health assessment system for use with a handheld electronic device for assessing cardiac health of a user and a method for assessing cardiac health of a user. The disclosure further relates to systems and methods for training a machine learning model to estimate intracardiac pressure data.
Claims16
A cardiac health assessment system for use with a handheld electronic device (HED) for assessing cardiac health of a user, characterized in the cardiac health assessment system comprising:
- an electronic device case (EDC) having a shape adapted to secure the handheld electronic device with the EDC, wherein the EDC comprises a sensor signal-enhancing material to amplify auscultation signals;
- and
- a circuit board configured within the EDC and electrically connected with a plurality of sensors, wherein the plurality of sensors comprise:
- a plurality of soundwave transducers to capture cardiac audio signals indicative of the cardiac health of the user;
- a plurality of photoplethysmography (PPG) sensors to capture visual data pertaining to tissue colour and/or blood flow;
- a plurality of Inertial Measurement Unit (IMU) sensors to capture seismic and auscultation signals indicative of the cardiac health of the user;
- and
- a microcontroller connected to the circuit board to transmit cardiac health data received from the plurality of sensors to a computing device over a network, wherein the computing device comprises a processor configured to:
- receive, in one or more temporal windows, representations of one or more signals recorded by the EDC, of at least one of the plurality of IMU sensors, the plurality of PPG sensors, and the plurality of soundwave transducers;
- detect features of the one or more signals from at least one or more portions of the received representations falling within each of the one or more temporal windows;
- and
- identify patterns of the features of respective sensors from within the at least one or more portions based on at least a classification model or a regression model.
9 more elements
Dependencies are inferred from the claim text.