We describe a method for creating and maintaining an open, annotated, community-moderated dataset of audio recordings of heart and lung sounds, with which to train machine listening systems to perform medical diagnosis. This is achieved by partnering with education programs for nursing and medical professionals who will receive training in diagnosis using digital stethoscopes. We developed a low-cost digital stethoscope using a peer-reviewed, open-source, 3-D printed design. With sufficiently numerous examples supplied and tagged by nursing and medical students, it is possible to employ machine learning classifiers such as our convolutional neural network code—originally developed for music information retrieval—to identify diagnosis classes. While primary intent of this dataset-creation and moderation system is for medical audio, the underlying functionality of community moderation could be applied to other waveform content, including a variety of musical datasets.
Skip Nav Destination
,
,
Article navigation
October 2017
Meeting abstract. No PDF available.
October 01 2017
Crowdsourcing the creation of an audio dataset for human and machine medical diagnosis training
Scott H. Hawley;
Scott H. Hawley
Chemistry & Physics, Belmont Univ., 1900 Belmont Blvd., Nashville, TN 37212, [email protected]
Search for other works by this author on:
Tamara Baird;
Tamara Baird
School of Nursing, Lipscomb Univ., Nashville, TN
Search for other works by this author on:
Frank Baird
Frank Baird
Recording and Entertainment, Middle Tennessee State Univ., Murfreesboro, TN
Search for other works by this author on:
Scott H. Hawley
Tamara Baird
Frank Baird
Chemistry & Physics, Belmont Univ., 1900 Belmont Blvd., Nashville, TN 37212, [email protected]
J. Acoust. Soc. Am. 142, 2612 (2017)
Citation
Scott H. Hawley, Tamara Baird, Frank Baird; Crowdsourcing the creation of an audio dataset for human and machine medical diagnosis training. J. Acoust. Soc. Am. 1 October 2017; 142 (4_Supplement): 2612. https://doi.org/10.1121/1.5014565
Download citation file:
97
Views
Citing articles via
I can't hear you without my glasses
Tessa Bent
A survey of sound source localization with deep learning methods
Pierre-Amaury Grumiaux, Srđan Kitić, et al.
Related Content
“Listening“ Crowdsourced Sound
J. Acoust. Soc. Am. (March 2018)
Music information retrieval—The impact of technology, crowdsourcing, big data, and the cloud in art
J. Acoust. Soc. Am. (October 2019)
Evaluating the use of crowdsourced data classification in an investigation of the steelpan drum
J. Acoust. Soc. Am. (October 2017)
A digital stethoscope with active noise suppression and automatic detection of abnormalities in lung sounds
J. Acoust. Soc. Am. (October 2020)
Introducing Feelix, a digital stethoscope incorporating active noise control and automatic detection of lung sound abnormalities
J. Acoust. Soc. Am. (March 2019)