Digital stethoscope for counting coughs, and applications thereof

Inventors

McLane, Ian Mitra

Assignees

Sonavi Labs Inc

Abstract

Embodiments disclosed herein improve digital stethoscopes and their application and operation. A first method detects of a respiratory abnormality using a convolution. A second method counts coughs for a patient. A third method predicts a respiratory event based on a detected trend. A fourth method forecasts characteristics of a future respiratory event. In a fifth embodiment, a base station is provided for a digital stethoscope.

Core Innovation

The invention provides one or more microphones configured to detect an auditory signal, and a field programmable gate array (FPGA) configured to receive the auditory signal and generate an auditory spectrogram based on the auditory signal. The FPGA performs a spatial convolution procedure on the auditory spectrogram to generate one or more convolution values, where the convolution values represent a compressed version of a matrix portion of the auditory spectrogram.

The spatial convolution procedure is trained to generate one or more features for detecting the respiratory abnormality, and the FPGA applies one or more weights to the convolution values. The weights are trained for detection of the respiratory abnormality, and a classification value is generated by applying the weights to the convolution values, where the classification value indicates when the auditory signal includes the respiratory abnormality.

The classification value is transmitted to a display unit for outputting the classification value, and the display unit is configured to display the classification value. The method further includes coupling the microphone to the FPGA, coupling the display unit to the FPGA, and integrating the microphone, the FPGA, and the display unit into a housing, thereby integrating the detection and output components into a digital stethoscope.

Claims Coverage

The provided independent claim covers the manufacture of a digital stethoscope for detecting a respiratory abnormality, including microphone-to-FPGA spectrogram generation, spatial convolution on spectrogram portions to produce compressed convolution values, trained weights for abnormality detection, generation of a classification value, and transmission of that classification value to a display unit integrated in a housing. The claim includes two further independent sub-steps specifying coupling of microphone and display to the FPGA and integration into the housing.

Across the independent claim, the inventive concept centers on an FPGA-based pipeline that converts microphone auditory signals into an auditory spectrogram, derives compressed convolution values via a trained spatial convolution procedure, uses trained weights to produce a classification value indicating respiratory abnormality, and outputs the classification value through a display unit integrated with the microphone and FPGA into a housing.

Stated Advantages

Documented Applications

No documented applications found