US 11,937,911 B2
Systems and methods for analyzing and monitoring lung function using voice and breath sound samples for respiratory care
Satya Venneti, Pittsburgh, PA (US); Mir Mohammed Daanish Ali Khan, Pittsburgh, PA (US); Rajat Kulshreshtha, Pittsburgh, PA (US); and Prakhar Pradeep Naval, Pittsburgh, PA (US)
Assigned to DeepConvo Inc., Pittsburgh, PA (US)
Filed by DeepConvo Inc., Pittsburgh, PA (US)
Filed on Nov. 25, 2020, as Appl. No. 17/105,332.
Application 17/105,332 is a continuation in part of application No. 16/931,429, filed on Jul. 16, 2020.
Claims priority of provisional application 62/941,477, filed on Nov. 27, 2019.
Prior Publication US 2021/0153772 A1, May 27, 2021
Int. Cl. A61B 5/08 (2006.01); A61B 5/00 (2006.01); G06N 20/00 (2019.01)
CPC A61B 5/0816 (2013.01) [A61B 5/7203 (2013.01); A61B 5/7275 (2013.01); A61B 5/741 (2013.01); G06N 20/00 (2019.01)] 16 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising:
receiving first streaming prompt data from a computing device;
analyzing the first streaming prompt data in real-time on a frame-by-frame basis;
providing feedback to a user of the computing device based on analysis of the first streaming prompt data;
upon determining the first streaming prompt data satisfies one or more criteria, receiving at least a subset of second streaming prompt data from the computing device, the subset of the second streaming prompt data comprising audio data representative of a first performed portion of a vocal action by the user; and
analyzing, prior to completion by the user of performance of one or more subsequent portions of the same vocal action, the subset of the second streaming prompt data for generation of a prediction of a respiratory state of the user of the computing device, wherein analyzing the subset of the second streaming prompt data further comprises:
analyzing audio data of the subset of the second streaming prompt data in real-time on the frame-by-frame basis;
wherein providing feedback comprises:
generating feedback at the computing device for the user, based on analysis of the subset of the second streaming prompt data.