| CPC A61B 5/0823 (2013.01) [A61B 5/0205 (2013.01); A61B 5/0816 (2013.01); A61B 5/7264 (2013.01); A61B 5/7275 (2013.01); A61B 7/003 (2013.01); A61B 7/04 (2013.01)] | 20 Claims |

|
1. A method of manufacture of a digital stethoscope for detection of a respiratory abnormality, the method comprising:
providing one or more microphones configured to detect an auditory signal;
providing a field programmable gate array (FPGA) configured to:
receive, from the one or more microphones, the auditory signal,
generate an auditory spectrogram based on the auditory signal,
perform a spatial convolution procedure on the auditory spectrogram to generate one or more convolution values, wherein the one or more convolution values represent a compressed version of a matrix portion of the auditory spectrogram, and wherein the spatial convolution procedure is trained to generate one or more features for detecting the respiratory abnormality,
apply one or more weights to the one or more convolution values wherein the weights are trained for detection of the respiratory abnormality,
generate a classification value based on applying the weights to the one or more convolution values, wherein the classification value indicates when the auditory signal includes the respiratory abnormality, and
transmit the classification value to a display unit for outputting the classification value, and wherein the display unit is configured to display the classification value;
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.
|