Heart and Lung Sound Recordings from a Clinical Manikin

HLS-CMDS contains audio recordings of heart and lung sounds captured using a digital stethoscope on a clinical manikin. The dataset is hosted on the UCI Machine Learning Repository and is tagged for auscultation and medical simulation. Its creator and exact size are not specified in the provided metadata.

Use Cases

• Classify lung sound types (e.g., crackles, wheezes) from audio waveforms for respiratory condition screening.
• Identify heart sound abnormalities (e.g., murmurs) from recorded audio segments for cardiac assessment.
• Train audio feature extraction models on labeled auscultation sounds from a controlled simulation environment.
• Benchmark signal processing techniques for noise reduction and enhancement of clinical stethoscope recordings.

Strengths

• Recordings captured in a controlled simulation environment using a digital stethoscope, reducing ambient noise variability.
• Dataset is hosted on the authoritative UCI Machine Learning Repository, ensuring stable access.

Limitations

• Data originates from a manikin, not human patients, which may limit clinical realism and model generalizability.
• The total number of audio samples, recording duration, and demographic context are unknown.

Provenance

Source

UCI Machine Learning Repository

Collection Method

Recorded from a clinical manikin using a digital stethoscope.